Deep fusion digital all-working-condition permanent magnet circuit breaker control system and method thereof

Abstract

The invention provides a deep fusion digital full-working-condition permanent magnet circuit breaker control system and method, and relates to the technical field of power equipment, and the method comprises the steps: based on a switch body, collecting circuit breaker switching signal data through a switching state quantity port, collecting circuit voltage signal data through a voltage transformer, and transmitting the collected circuit voltage signal data to a controller; circuit current signal data are collected through a current transformer, the data are gathered to generate circuit breaker analog signal data, the circuit breaker analog signal data are converted into circuit breaker digital signal data and transmitted to a digital feeder terminal, the on-off state of a circuit breaker is monitored according to the circuit breaker digital signal data, and current circuit fault information is recognized. The circuit operation state prediction model is constructed, and the future circuit operation state is predicted according to the on-off state of the circuit breaker and the current circuit fault information, so that double-end voltage acquisition can be realized, the anti-interference capability is relatively high, the measurement precision can be improved, and the comprehensive accuracy of the system can be ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment, and in particular to a control system and method for a deeply integrated digital full-condition permanent magnet circuit breaker. Background Art

[0002] Most of the existing integrated primary and secondary pole-mounted circuit breakers adopt spring mechanism circuit breakers. The deeply integrated type adopts electronic voltage and current sensors in the form of current transformers, and the output signal current is 600A / 1V and the voltage is 10kV / 3.25V. Therefore, although it has the characteristics of low power consumption and safety of traditional electromagnetic transformers and the characteristics of high precision and wide range under low load conditions, in actual applications, the anti-interference ability of small voltage signals is weak. Even when shielded cable is used for transmission, within a transmission distance of 8 meters, it may be interfered, resulting in distortion of the original power frequency signal volume, triggering real-time waveform distortion alarms, and even causing the circuit breaker to trip falsely. And the existing technology can only achieve single-end voltage signal acquisition, and for medium-voltage lines in some areas, it cannot be used as a tie switch to meet the dual-end voltage acquisition requirements and realize in-situ distribution automation.

[0003] Therefore, it is necessary to provide a control system and method for a deeply integrated digital full-condition permanent magnet circuit breaker to solve the above technical problems. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a control system and method for a deeply integrated digital full-condition permanent magnet circuit breaker, which is used to solve the problems of weak anti-interference ability of small voltage signals and inability to achieve dual-end voltage acquisition in the prior art.

[0005] A control system for a deeply integrated digital full-condition permanent magnet circuit breaker provided by the present invention, the system includes: A switch body acquisition module, configured to collect circuit breaker switch signal data through a switch status quantity port based on the switch body, collect circuit voltage signal data through a voltage transformer, and collect circuit current signal data through a current transformer; An analog signal generation module, configured to summarize the circuit breaker switch signal data, the circuit voltage signal data, and the circuit current signal data to generate circuit breaker analog signal data; A digital conversion and transmission module, configured to convert the circuit breaker analog signal data into circuit breaker digital signal data and transmit it to a digital feeder terminal; A terminal monitoring and identification module, configured to monitor the circuit breaker switch status and identify current circuit fault information based on the digital feeder terminal according to the circuit breaker digital signal data; The operating status prediction module is used to build a circuit operating status prediction model and predict the future circuit operating status based on the breaker switch status and the current circuit fault information.

[0006] Preferably, the voltage transformer includes an infeed side capacitive voltage transformer and an outfeed side capacitive voltage transformer, and the circuit voltage signal data includes power supply side voltage signal data and load side voltage signal data; Collect the power supply side voltage signal data through the infeed side capacitive voltage transformer; and collect the load side voltage signal data through the outfeed side capacitive voltage transformer.

[0007] Preferably, the analog signal generation module is built in the switch body acquisition module.

[0008] Preferably, the digital conversion and transmission module is used to convert the breaker analog signal data into breaker digital signal data and transmit it to the digital feeder terminal, specifically including: The receiving and processing unit is used to receive the breaker analog signal data and perform filtering and amplification processing on the breaker analog signal data; The signal conversion unit is used to convert the breaker analog signal data into the breaker digital signal data through a high-precision analog-to-digital converter; The signal transmission unit is used to pack the breaker digital signal data into a data frame and transmit the data frame to the digital feeder terminal through an RS485 simplex communication method using a twisted shielded cable.

[0009] Preferably, the signal amplitude range of the breaker digital signal data is 3V to 10V peak-to-peak, the transmission speed is 5Mbit / s, and the Manchester coding method is adopted; The twisted shielded cable adopts a 10-core remote control cable, and the 10-core remote control cable includes 2-core communication cables, 2-core power cables, and 6-core control signal cables.

[0010] Preferably, the terminal monitoring and identification module is used to monitor the breaker switch status and identify the current circuit fault information based on the digital feeder terminal according to the breaker digital signal data, specifically including: Based on the digital feeder terminal, the breaker switch status is monitored in real time according to the breaker digital signal data, and the switch status features corresponding to the breaker switch status are extracted. When the switch status features are classified based on a support vector machine, the corresponding optimization problem is as follows: In the formula, represents the weight of the u-th support vector machine and is used to determine the direction of the classification hyperplane; It represents the bias term of the $u$-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; It represents the slack variable when the $v$-th switch state feature is linearly inseparable in the $u$-th support vector machine; $C$ represents the regularization parameter, which is used to control the trade-off between the classification margin and classification error; $R$ represents the number of switch state features; $\min$ represents the minimum value operation.

[0011] Preferably, the constraint conditions corresponding to the optimization problem are as follows: In the formula, It represents the feature class label corresponding to the $v$-th switch state feature; It represents the $v$-th switch state feature; It represents the weight of the $u$-th support vector machine, which is used to determine the direction of the classification hyperplane; It represents the bias term of the $u$-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; It represents the slack variable when the $v$-th switch state feature is linearly inseparable in the $u$-th support vector machine; $R$ represents the number of switch state features; Based on the feature classification result of the switch state feature, determine the switch state of the circuit breaker.

[0012] Preferably, if the switch state of the circuit breaker is a fault state, then identify the current circuit fault information according to the digital signal data of the circuit breaker, which specifically includes: Extract the circuit breaker digital signal features corresponding to the circuit breaker digital signal data, and use the circuit breaker digital signal features as the input to initialize the features of node $j$ corresponding to the circuit breaker digital signal data. The corresponding calculation formula is as follows: In the formula, It represents the initial feature of node $j$; It represents the input feature of node $j$, that is, the circuit breaker digital signal feature; In the $l$-th layer where node $j$ is located, the calculation formula for message passing from node $i$ to node $j$ is as follows: In the formula, It represents the message from node $i$ to node $j$ in the $l$-th layer; It represents the message passing weight in the $l$-th layer; It represents the vector concatenation operation; It represents the feature of node $i$ in the $(l - 1)$-th layer; It represents the feature of node $j$ in the $(l - 1)$-th layer; It represents the edge feature from node $i$ to node $j$; The calculation formula for the message aggregation of node j in the l-th layer is as follows: In the formula, represents the message after aggregation of node j in the l-th layer; represents the message from node i to node j in the l-th layer; represents the set of neighbor nodes of node j; The calculation formula for the feature update of node j in the l-th layer is as follows: In the formula, represents the updated feature of node j in the l-th layer; represents the feature update activation function; represents the feature update weight of the l-th layer; represents the feature of node i in the (l - 1)-th layer; represents the message after aggregation of node j in the l-th layer; represents the feature update bias term of the l-th layer; The calculation formula for the output of node j is as follows: In the formula, represents the output of node j, that is, the probability that node j is a fault point; represents the output function; represents the weight of the output layer; represents the updated feature of node j in the l-th layer; represents the bias term of the output layer; If the probability that node j is a fault point is greater than or equal to the preset critical fault probability, then it is determined that node j is the current circuit fault point, and the current circuit fault information is generated.

[0013] Preferably, the operation state prediction module is used to construct a circuit operation state prediction model and predict the future circuit operation state according to the breaker switch state and the current circuit fault information, specifically including: Summarize the breaker switch state and the current circuit fault information to generate the current circuit operation state data; Based on the circuit operation state prediction model, predict the future circuit operation state according to the current circuit operation state data; Input the current circuit operation state data into the forget gate of the circuit operation state prediction model to determine the current circuit operation state data that needs to be discarded from the memory unit, and the corresponding calculation formula is as follows: In the formula, represents the output of the forget gate at the current time t, which is used to determine the current circuit operation state data that needs to be discarded from the memory unit; The activation function representing the forget gate; The weights of the forget gate; Represents the hidden state at the previous time step t-1; Represents the current circuit operating state data input at the current time step t; Represents the hidden state and the current circuit operating state data to form a vector; The bias term of the forget gate; Based on the input gate of the circuit operating state prediction model, determine the current circuit operating state data to be stored in the memory cell, and the corresponding calculation formula is as follows: In the formula, Represents the output of the input gate at the current time step t, which is used to determine the current circuit operating state data to be stored in the memory cell; The activation function representing the input gate; The weights of the input gate; Represents the hidden state at the previous time step t-1; Represents the current circuit operating state data input at the current time step t; Represents the hidden state and the current circuit operating state data to form a vector; The bias term of the input gate; Based on the candidate memory cells of the circuit operating state prediction model, determine the predicted circuit operating state data, and the corresponding calculation formula is as follows: In the formula, Represents the candidate memory cell at the current time step t, which is used to determine the predicted circuit operating state data; Represents the hyperbolic tangent function; The weights of the candidate memory cell; Represents the hidden state at the previous time step t-1; Represents the current circuit operating state data input at the current time step t; Represents the hidden state and the current circuit operating state data to form a vector; The bias term of the candidate memory cell; The calculation formula for updating the memory cell is as follows: In the formula, Represents the cell state at the current time step t; Represents the output of the forget gate at the current time step t; Indicates the cell state at the previous time t-1; Represents the output of the input gate at the current time t; represents the candidate cell state at the current time t; Based on the output gate of the circuit operation state prediction model, the predicted circuit operation state data to be output to the hidden state is determined, and the corresponding calculation formula is as follows: In the formula, The output of the output gate at the current time t is used to determine the predicted circuit operation state data that needs to be output to the hidden state; represents the activation function of the output gate; represents the output of the output gate; Represents the hidden state at the previous moment t-1; Represents the current circuit operation status data input at the current time t; Indicates hidden state and current circuit operation status data The vector composed of Represents the bias term of the output gate; According to the cell state at the current time t and the output of the output gate, the future circuit operation state is predicted, and the corresponding calculation formula is as follows: In the formula, represents the hidden state at the current time t, that is, the predicted future circuit operation state; represents the hyperbolic tangent function; Represents the cell state at the current time t.

[0014] A deeply integrated digital full-operating condition permanent magnet circuit breaker control method, the method comprising: Based on the switch body, the switch signal data of the circuit breaker is collected through the switch status port, the circuit voltage signal data is collected through the voltage transformer, and the circuit current signal data is collected through the current transformer; Aggregating the circuit breaker switch signal data, the circuit voltage signal data and the circuit current signal data to generate circuit breaker simulation signal data; Converting the circuit breaker analog signal data into circuit breaker digital signal data and transmitting the data to the digital feeder terminal; Based on the digital feeder terminal, monitoring the circuit breaker switch state and identifying current circuit fault information according to the circuit breaker digital signal data; A circuit operation state prediction model is constructed, and the future circuit operation state is predicted according to the circuit breaker switch state and the current circuit fault information.

[0015] Compared with the related technologies, a deep fusion digital full-condition permanent magnet circuit breaker control system and method provided by the present invention have the following beneficial effects: The present invention includes a switch body acquisition module, an analog signal generation module, a digital conversion and transmission module, a terminal monitoring and identification module, and an operating state prediction module. Based on the switch body, it can collect circuit breaker switch signal data through the switch status port, collect circuit voltage signal data through a voltage transformer, and collect circuit current signal data through a current transformer; summarize the circuit breaker switch signal data, circuit voltage signal data, and circuit current signal data to generate circuit breaker analog signal data; convert the circuit breaker analog signal data into circuit breaker digital signal data and transmit it to a digital feeder terminal; based on the digital feeder terminal, monitor the circuit breaker switch status and identify the current circuit fault information according to the circuit breaker digital signal data; construct a circuit operating state prediction model, and predict the future circuit operating state according to the circuit breaker switch status and the current circuit fault information, so as to achieve dual-end voltage acquisition, have strong anti-interference ability, and can improve the measurement accuracy and ensure the overall system accuracy.

[0016] The present invention avoids the interference of environmental factors through digital transmission, has strong anti-interference ability, and has obvious advantages in signal lossless transmission; and can realize the real-time acquisition of three-phase voltage, zero-sequence voltage, three-phase measurement and protection current, and zero-sequence measurement and protection current on the power supply side and the load side. In addition, the digital current sensor can reach a metering accuracy of 0.2 level, compared with the 0.5 level of the existing electronic sensors, which greatly improves the metering accuracy and ensures the overall system accuracy of 0.2S / 0.5S level; the present invention can digitize analog signals locally, and only one 10-core remote control cable is required to meet the three-remote signal transmission of complete sets of equipment, reducing the telemetry cable between primary and secondary equipment, and solving the anti-interference and isolation problems during long-line transmission; at the same time, digital signals can be directly processed by the digital feeder terminal, without building analog and digital quantity acquisition circuits, meeting the application scenario requirements of local feeder automation for double-power connection switches in medium-voltage distribution network lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a system block diagram of a deep fusion digital full-condition permanent magnet circuit breaker control system of the present invention; Figure 2 It is a structural block diagram of the digital conversion and transmission module of a deep fusion digital full-condition permanent magnet circuit breaker control system of the present invention; Figure 3 It is a flowchart of a deep fusion digital full-condition permanent magnet circuit breaker control method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0019] Embodiment 1

[0020] As Figure 1 shown, a fully digital permanent magnet circuit breaker control system with deep integration, the system includes: A switch body acquisition module, which is used to collect circuit breaker switch signal data through the switch status port based on the switch body, collect circuit voltage signal data through a voltage transformer, and collect circuit current signal data through a current transformer; An analog signal generation module, which is used to summarize the circuit breaker switch signal data, the circuit voltage signal data, and the circuit current signal data to generate circuit breaker analog signal data; A digital conversion and transmission module, which is used to convert the circuit breaker analog signal data into circuit breaker digital signal data and transmit it to a digital feeder terminal; A terminal monitoring and identification module, which is used to monitor the circuit breaker switch status and identify the current circuit fault information based on the digital feeder terminal according to the circuit breaker digital signal data; An operating state prediction module, which is used to construct a circuit operating state prediction model and predict the future circuit operating state according to the circuit breaker switch status and the current circuit fault information.

[0021] Among them, based on the switch body, the switch signal data of the circuit breaker can be collected in real time through the switch status port, including remote signaling signals such as opening / closing status, energy storage status, and low air pressure alarm. At the same time, through the double-circuit high-voltage capacitive voltage transformers on the incoming and outgoing lines, the three-phase voltage and zero-sequence voltage signal data on the power supply side and the load side can be collected, and through the current transformer, the three-phase current and zero-sequence current signal data can be collected to ensure the accuracy of electrical quantity collection under all working conditions.

[0022] Furthermore, the collected circuit breaker switch signal data, circuit voltage signal data, and circuit current signal data can be summarized and integrated to generate analog signal data including the operating state of the circuit breaker and the electrical parameters of the circuit. Then, through a high-precision analog-to-digital converter, the generated circuit breaker analog signal data can be converted into digital signal data and transmitted to the digital feeder terminal through a high-speed communication interface to ensure the anti-interference ability and data integrity during the signal transmission process.

[0023] In addition, based on the digital feeder terminal, the received circuit breaker digital signal data can be analyzed in real time, and then the switch status of the circuit breaker can be monitored, fault information such as overcurrent, short circuit, and grounding in the circuit can be identified, and corresponding fault alarms can be generated.

[0024] Finally, a circuit operation status prediction model based on historical data and real-time data can be constructed. By combining the breaker switch status and current circuit fault information, the future circuit operation trend and potential risks can be predicted to improve the reliability and intelligence level of power grid operation.

[0025] In the specific implementation process, the voltage transformer includes an infeed side capacitive voltage transformer and an outfeed side capacitive voltage transformer, and the circuit voltage signal data includes power supply side voltage signal data and load side voltage signal data. The power supply side voltage signal data is collected through the infeed side capacitive voltage transformer; and the load side voltage signal data is collected through the outfeed side capacitive voltage transformer.

[0026] It should be noted that the voltage transformer consists of two parts, namely an infeed side capacitive voltage transformer and an outfeed side capacitive voltage transformer. The infeed side capacitive voltage transformer is used to monitor the voltage signal data of the power supply side; the outfeed side capacitive voltage transformer is used to monitor the voltage signal data of the load side.

[0027] Through this dual-channel design, the voltage information of both the power supply side and the load side can be obtained simultaneously to ensure comprehensive monitoring of the operation status of the power system. This configuration not only improves the accuracy and reliability of voltage signal acquisition but also effectively supports the functions of fault detection, location, and isolation in the distribution automation system. Especially in the application scenario of a dual-power tie switch, it can provide accurate voltage data support for power supply switching and load transfer, thereby improving the power supply reliability and operation efficiency of the distribution network.

[0028] The analog signal generation module is built in the switch body acquisition module.

[0029] As Figure 2 shown, the digital conversion and transmission module 200 is used to convert the breaker analog signal data into breaker digital signal data and transmit it to the digital feeder terminal, specifically including: A receiving and processing unit 201, which is used to receive the breaker analog signal data and perform filtering and amplification processing on the breaker analog signal data; A signal conversion unit 202, which is used to convert the breaker analog signal data into the breaker digital signal data through a high-precision analog-to-digital converter; A signal transmission unit 203, which is used to pack the breaker digital signal data into a data frame and transmit the data frame to the digital feeder terminal through an RS485 simplex communication method using a twisted pair shielded cable.

[0030] It can be understood that the digital conversion and transmission module can convert the analog signal data collected by the circuit breaker into digital signal data and transmit it to the digital feeder terminal through the communication interface.

[0031] Specifically, the receiving and processing unit can receive the analog signal data from the circuit breaker and perform filtering and amplification processing on it to ensure the signal quality. The signal conversion unit can convert the processed analog signal data into digital signal data through a high-precision analog-to-digital converter to ensure the accuracy and stability during the conversion process. The signal transmission unit can package the converted digital signal data into data frames that conform to the communication protocol and transmit the data frames to the digital feeder terminal through the RS485 simplex communication method using a twisted pair shielded cable to ensure the anti-interference ability and reliability of the signal during transmission.

[0032] The signal amplitude range of the digital signal data of the circuit breaker is 3V to 10V peak-to-peak, the transmission speed is 5Mbit / s, and the Manchester coding method is adopted; The twisted pair shielded cable uses a 10-core remote control cable, and the 10-core remote control cable includes 2-core communication cables, 2-core power cables, and 6-core control signal cables.

[0033] In practical applications, the signal amplitude range of the digital signal data of the circuit breaker is 3V to 10V peak-to-peak, the transmission speed is 5Mbit / s, and the Manchester coding method is used for data transmission to ensure the anti-interference ability and data integrity of the signal during transmission.

[0034] It should be noted that the Manchester coding method can effectively avoid the problem of DC components in signal transmission by combining the clock signal with the data signal, while improving the synchronization and reliability of the signal.

[0035] The twisted pair shielded cable uses a 10-core remote control cable, and the cable structure includes 2-core communication cables, 2-core power cables, and 6-core control signal cables. Among them, the communication cables are used to transmit digital signal data; the power cables provide a stable power supply for the equipment; the control signal cables are used to transmit control signals such as the opening and closing of the circuit breaker and the energy storage state. Through this design, while ensuring the signal transmission quality, it can simplify the cable wiring, improve the overall reliability of the system, and the convenience of maintenance.

[0036] The terminal monitoring and identification module is used to monitor the circuit breaker switch state and identify the current circuit fault information based on the digital feeder terminal according to the digital signal data of the circuit breaker, specifically including: Based on the digital feeder terminal, the switch state of the circuit breaker is monitored in real time according to the digital signal data of the circuit breaker, and the switch state features corresponding to the switch state of the circuit breaker are extracted. When performing feature classification on the switch state features based on the support vector machine, the corresponding optimization problem is as follows: In the formula, represents the weight of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the slack variable when the v-th switch state feature is linearly inseparable in the u-th support vector machine; C represents the regularization parameter, which is used to control the trade-off between the classification margin and classification error; R represents the number of switch state features; min represents the operation of taking the minimum value.

[0037] The constraint conditions corresponding to the optimization problem are as follows: In the formula, represents the feature class label corresponding to the v-th switch state feature; represents the v-th switch state feature; represents the weight of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the slack variable when the v-th switch state feature is linearly inseparable in the u-th support vector machine; R represents the number of switch state features; Based on the feature classification result of the switch state features, the switch state of the circuit breaker is determined.

[0038] It can be understood that the terminal monitoring and recognition module can collect the digital signal data of the switch state of the circuit breaker through the digital feeder terminal, extract the switch state features, and classify the features using the support vector machine algorithm.

[0039] The support vector machine determines the direction and position of the classification hyperplane by solving the optimization problem. Among them, the weight parameter is used to determine the direction of the classification hyperplane, the bias term is used to adjust the distance between the classification hyperplane and the origin, the slack variable is used to handle the linearly inseparable situation, and the regularization parameter is used to balance the weight between the classification margin and classification error. The constraint conditions of the optimization problem can ensure that each switch state feature satisfies the relationship between the class label and the classification hyperplane during the classification process.

[0040] Based on the classification result of the switch state features, the terminal monitoring and recognition module can accurately identify the switch state of the circuit breaker, and then generate circuit fault information, providing a reliable basis for fault location and isolation.

[0041] If the circuit breaker switch state is a fault state, then identify the current circuit fault information according to the circuit breaker digital signal data, specifically including: Extract the circuit breaker digital signal characteristics corresponding to the circuit breaker digital signal data, and use the circuit breaker digital signal characteristics as the input to initialize the characteristics of node j corresponding to the circuit breaker digital signal data. The corresponding calculation formula is as follows: In the formula, represents the initial characteristic of node j; represents the input characteristic of node j, that is, the circuit breaker digital signal characteristic; In the l-th layer where node j is located, the calculation formula for message passing from node i to node j is as follows: In the formula, represents the message from node i to node j in the l-th layer; represents the message passing weight in the l-th layer; represents the vector concatenation operation; represents the characteristic of node i in the (l - 1)-th layer; represents the characteristic of node j in the (l - 1)-th layer; represents the edge characteristic from node i to node j; The calculation formula for message aggregation of node j in the l-th layer is as follows:

[0042] In the formula, represents the aggregated message of node j in the l-th layer; represents the message from node i to node j in the l-th layer; represents the set of neighbor nodes of node j; The calculation formula for feature update of node j in the l-th layer is as follows: In the formula, represents the updated characteristic of node j in the l-th layer; represents the feature update activation function; represents the feature update weight in the l-th layer; represents the characteristic of node i in the (l - 1)-th layer; represents the aggregated message of node j in the l-th layer; represents the feature update bias term in the l-th layer; The calculation formula for the output of node j is as follows: In the formula, represents the output of node j, that is, the probability that node j is a fault point; Represents the output function; Represents the weights of the output layer; Represents the updated feature of node j in the l-th layer; Represents the bias term of the output layer; If the probability that the node j is a fault point is greater than or equal to the preset critical fault probability, then it is determined that the node j is the current circuit fault point, and the current circuit fault information is generated.

[0043] In practical applications, first, the circuit breaker digital signal features corresponding to the circuit breaker digital signal data can be extracted, and the circuit breaker digital signal features are used as inputs to initialize the features of node j corresponding to the circuit breaker digital signal data.

[0044] Among them, the initial feature of node j is determined by its input feature, that is, the circuit breaker digital signal feature. When message passing from node i to node j in the l-th layer where node j is located, the calculation of message passing is based on the features of node i and node j in the previous layer, the edge feature from node i to node j, and the message passing weight matrix.

[0045] Furthermore, when node j performs message aggregation in the l-th layer, the aggregation process generates the aggregated message of node j by summing the passed messages of all its neighbor nodes. Then, node j can perform feature update in the l-th layer, and its update process combines the feature of node j in the previous layer with the aggregated message through an activation function, and adds the feature update weight and bias term to generate the updated feature of node j.

[0046] Finally, the output of node j is calculated through the output function, and the output function can combine the updated feature of node j with the output layer weights and bias term to determine the probability that node j is a fault point. If the probability that node j is a fault point is greater than or equal to the preset critical fault probability, then it is determined that node j is the current circuit fault point, and the corresponding circuit fault information is generated.

[0047] The operating state prediction module is used to construct a circuit operating state prediction model and predict the future circuit operating state according to the circuit breaker switch state and the current circuit fault information, specifically including: Summarize the circuit breaker switch state and the current circuit fault information to generate the current circuit operating state data; Based on the circuit operating state prediction model, predict the future circuit operating state according to the current circuit operating state data; Input the current circuit operating state data into the forget gate of the circuit operating state prediction model to determine the current circuit operating state data that needs to be discarded from the memory unit, and the corresponding calculation formula is as follows: In the formula, Represents the output of the forget gate at the current time t, which is used to determine the current circuit operating state data to be discarded from the memory cell; Represents the activation function of the forget gate; Represents the weight of the forget gate; Represents the hidden state at the previous time t-1; Represents the current circuit operating state data input at the current time t; Represents the hidden state and the current circuit operating state data to form a vector; Represents the bias term of the forget gate; Based on the input gate of the circuit operating state prediction model, determine the current circuit operating state data to be stored in the memory cell. The corresponding calculation formula is as follows: In the formula, Represents the output of the input gate at the current time t, which is used to determine the current circuit operating state data to be stored in the memory cell; Represents the activation function of the input gate; Represents the weight of the input gate; Represents the hidden state at the previous time t-1; Represents the current circuit operating state data input at the current time t; Represents the hidden state and the current circuit operating state data to form a vector; Represents the bias term of the input gate; Based on the candidate memory cell of the circuit operating state prediction model, determine the predicted circuit operating state data. The corresponding calculation formula is as follows: In the formula, Represents the candidate memory cell at the current time t, which is used to determine the predicted circuit operating state data; Represents the hyperbolic tangent function; Represents the weight of the candidate memory cell; Represents the hidden state at the previous time t-1; Represents the current circuit operating state data input at the current time t; Represents the hidden state and the current circuit operating state data to form a vector; Represents the bias term of the candidate memory cell; The calculation formula for updating the memory cell is as follows: In the formula, Represents the cell state at the current time t; Represents the output of the forget gate at the current time t; Represents the cell state at the previous time t-1; Represents the output of the input gate at the current time t; Represents the candidate cell state at the current time t; Based on the output gate of the circuit operating state prediction model, determine the predicted circuit operating state data that needs to be output to the hidden state. The corresponding calculation formula is as follows: In the formula, Represents the output of the output gate at the current time t, which is used to determine the predicted circuit operating state data that needs to be output to the hidden state; Represents the activation function of the output gate; Represents the output of the output gate; Represents the hidden state at the previous time t-1; Represents the current circuit operating state data input at the current time t; Represents the hidden state And the current circuit operating state data Composed vector; Represents the bias term of the output gate; According to the cell state at the current time t and the output of the output gate, predict the future circuit operating state. The corresponding calculation formula is as follows: In the formula, Represents the hidden state at the current time t, that is, the predicted future circuit operating state; Represents the hyperbolic tangent function; Represents the cell state at the current time t.

[0048] In practical applications, the operating state prediction module can build an accurate circuit operating state prediction model and estimate the future circuit operating state according to the specific state of the circuit breaker switch and the current circuit fault information.

[0049] Specifically, first, the circuit breaker switch state and the current circuit fault information can be summarized to form the current circuit operating state data set. Then, the circuit operating state prediction model can be used to predict the future circuit operating state based on the current data set. During this process, the current circuit operating state data can be input into the forget gate of the prediction model to determine the data that needs to be discarded from the memory unit. Then, the input gate can be used to determine the data that needs to be stored in the memory unit.

[0050] Furthermore, the predicted circuit operating state data can be determined through the candidate memory cells, and the memory unit can be updated by combining the current forget gate output, the previous cell state, the current input gate output, and the candidate cell state.

[0051] Finally, the predicted circuit operating state data to be output to the hidden state can be determined based on the output gate, and the hidden state at the current moment, i.e., the future circuit operating state, can be determined according to the current cell state and the output of the output gate.

[0052] Embodiment 2

[0053] As Figure 3 shown, a control method for a deeply integrated digital full-condition permanent magnet circuit breaker, the method comprising: S1, based on the switch body, collecting circuit breaker switch signal data through a switch status quantity port, collecting circuit voltage signal data through a voltage transformer, and collecting circuit current signal data through a current transformer; S2, summarizing the circuit breaker switch signal data, the circuit voltage signal data, and the circuit current signal data to generate circuit breaker analog signal data; S3, converting the circuit breaker analog signal data into circuit breaker digital signal data and transmitting it to a digital feeder terminal; S4, based on the digital feeder terminal, monitoring the circuit breaker switch state and identifying current circuit fault information according to the circuit breaker digital signal data; S5, constructing a circuit operating state prediction model, and predicting the future circuit operating state according to the circuit breaker switch state and the current circuit fault information.

[0054] Through the introduction of the above embodiments, the present invention provides a deeply integrated digital full-condition permanent magnet circuit breaker control system and method thereof, including a switch body acquisition module, an analog signal generation module, a digital conversion and transmission module, a terminal monitoring and identification module, and an operating state prediction module. It can collect circuit breaker switch signal data through a switch status quantity port based on the switch body, collect circuit voltage signal data through a voltage transformer, and collect circuit current signal data through a current transformer; summarize the circuit breaker switch signal data, the circuit voltage signal data, and the circuit current signal data to generate circuit breaker analog signal data; convert the circuit breaker analog signal data into circuit breaker digital signal data and transmit it to a digital feeder terminal; based on the digital feeder terminal, monitor the circuit breaker switch state and identify current circuit fault information according to the circuit breaker digital signal data; construct a circuit operating state prediction model, and predict the future circuit operating state according to the circuit breaker switch state and the current circuit fault information, thereby enabling dual-terminal voltage acquisition, having strong anti-interference ability, and being able to improve measurement accuracy and ensure the overall accuracy of the system.

[0055] The present invention transmits digitally, avoiding the interference of environmental factors, having strong anti-interference ability, and having obvious advantages in signal lossless transmission. Moreover, it can realize the real-time acquisition of three-phase voltages, zero-sequence voltages, three-phase measured and protected currents, and zero-sequence measured and protected currents on the power supply side and the load side. In addition, the digital current sensor can achieve a metering accuracy of 0.2 level, which is a significant improvement compared to the 0.5 level of the existing electronic sensors, ensuring the system comprehensive accuracy of 0.2S / 0.5S level. The present invention can digitize analog signals locally, and only one 10-core remote control cable is required to meet the three-remote signal transmission of complete sets of equipment, reducing the telemetry cables between primary and secondary equipment and solving the anti-interference and isolation problems in the long-line transmission process. At the same time, it can directly process digital signals through the digital feeder terminal without building analog and digital quantity acquisition circuits, meeting the application scenario requirements of the local feeder automation of the double-power connection switch on the medium-voltage distribution network line.

[0056] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0057] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disc memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0058] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent in such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

Claims

1. A digital full-condition permanent magnet circuit breaker control system with deep integration, characterized in that The system includes: A switch body acquisition module, which is used to collect breaker switch signal data through a switch status quantity port based on the switch body, collect circuit voltage signal data through a voltage transformer, and collect circuit current signal data through a current transformer; An analog signal generation module, which is used to summarize the breaker switch signal data, the circuit voltage signal data, and the circuit current signal data to generate breaker analog signal data; A digital conversion and transmission module, which is used to convert the breaker analog signal data into breaker digital signal data and transmit it to a digital feeder terminal; A terminal monitoring and identification module, which is used to monitor the breaker switch status and identify current circuit fault information based on the digital feeder terminal according to the breaker digital signal data; An operating state prediction module, which is used to construct a circuit operating state prediction model and predict the future circuit operating state according to the breaker switch status and the current circuit fault information.

2. The digital full-condition permanent magnet circuit breaker control system with deep fusion according to claim 1, wherein The voltage transformer includes an in-line capacitive voltage transformer and an out-line capacitive voltage transformer, and the circuit voltage signal data includes power supply side voltage signal data and load side voltage signal data; Collect the power supply side voltage signal data through the in-line capacitive voltage transformer; and collect the load side voltage signal data through the out-line capacitive voltage transformer.

3. The digital full-condition permanent magnet circuit breaker control system with deep integration according to claim 1, characterized in that, The analog signal generation module is built in the switch body acquisition module.

4. A digital full-condition permanent magnet circuit breaker control system with deep integration according to claim 1, characterized in that, The digital conversion and transmission module, which is used to convert the breaker analog signal data into breaker digital signal data and transmit it to a digital feeder terminal, specifically includes: A receiving and processing unit, which is used to receive the breaker analog signal data and perform filtering and amplification processing on the breaker analog signal data; A signal conversion unit, which is used to convert the breaker analog signal data into the breaker digital signal data through a high-precision analog-to-digital converter; A signal transmission unit, which is used to package the breaker digital signal data into a data frame and transmit the data frame to the digital feeder terminal through a RS485 simplex communication method using a twisted pair shielded cable.

5. The digital full-condition permanent magnet circuit breaker control system with deep integration according to claim 4, characterized in that, The signal amplitude range of the breaker digital signal data is 3V to 10V peak-to-peak, the transmission speed is 5Mbit / s, and the Manchester coding method is adopted; The twisted pair shielded cable uses a 10-core remote control cable, and the 10-core remote control cable includes 2-core communication cables, 2-core power cables, and 6-core control signal cables.

6. The digital full-condition permanent magnet circuit breaker control system with deep fusion according to claim 1, wherein The terminal monitoring and identification module, which is used to monitor the breaker switch status and identify current circuit fault information based on the digital feeder terminal according to the breaker digital signal data, specifically includes: Based on the digital feeder terminal, the breaker switch status is monitored in real time according to the breaker digital signal data, and the switch status characteristics corresponding to the breaker switch status are extracted. When the switch status characteristics are classified based on a support vector machine, the corresponding optimization problem is as follows: In the formula, represents the weight of the \(u\)-th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the \(u\)-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the slack variable when the \(v\)-th switch state feature is linearly inseparable in the \(u\)-th support vector machine; \(C\) represents the regularization parameter, which is used to control the trade-off between the classification margin and classification error; \(R\) represents the number of switch state features; min represents the operation of taking the minimum value.

7. The digital full-condition permanent magnet circuit breaker control system with deep fusion according to claim 6, characterized in that, The constraint conditions corresponding to the optimization problem are as follows: In the formula, represents the feature category label corresponding to the v-th switch state feature; represents the v-th switch state feature; represents the weight of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; represents the slack variable when the v-th switch state feature is linearly inseparable in the u-th support vector machine; R represents the number of switch state features; Determine the breaker switch status based on the feature classification result of the switch status characteristics.

8. A digital full-condition permanent magnet circuit breaker control system with deep integration according to claim 7, characterized in that, If the circuit breaker switch state is a fault state, then identify the current circuit fault information according to the circuit breaker digital signal data, specifically including: Extract the circuit breaker digital signal features corresponding to the circuit breaker digital signal data, and use the circuit breaker digital signal features as input to initialize the features of node j corresponding to the circuit breaker digital signal data. The corresponding calculation formula is as follows: In the formula, represents the initial feature of node j; represents the input feature of node j, that is, the digital signal feature of the circuit breaker; In the l-th layer where node j is located, the calculation formula for message passing from node i to node j is as follows: In the formula, represents the message from node i to node j in the l-th layer; represents the message passing weight in the l-th layer; represents the vector concatenation operation; represents the feature of node i in the (l - 1)-th layer; represents the feature of node j in the (l - 1)-th layer; represents the edge feature from node i to node j; The calculation formula for message aggregation of node j in the l-th layer is as follows: In the formula, represents the message aggregated by node j in the l-th layer; represents the message from node i to node j in the l-th layer; represents the set of neighbor nodes of node j; The calculation formula for feature update of node j in the l-th layer is as follows: In the formula, represents the updated feature of node j in the l-th layer; represents the feature update activation function; represents the feature update weight of the l-th layer; represents the feature of node i in the (l - 1)-th layer; represents the aggregated message of node j in the l-th layer; represents the feature update bias term of the l-th layer; The calculation formula for the output of node j is as follows: In the formula, represents the output of node j, that is, the probability that node j is the fault point; represents the output function; represents the weight of the output layer; represents the updated feature of node j in the l-th layer; represents the bias term of the output layer; If the probability that node j is a fault point is greater than or equal to the preset critical fault probability, then determine that node j is the current circuit fault point and generate the current circuit fault information.

9. A fully digital permanent magnet circuit breaker control system for deep integration under all operating conditions according to claim 1, characterized in that The operating state prediction module is used to construct a circuit operating state prediction model and predict the future circuit operating state according to the circuit breaker switch state and the current circuit fault information, specifically including: Summarize the circuit breaker switch state and the current circuit fault information to generate the current circuit operating state data; Based on the circuit operating state prediction model, predict the future circuit operating state according to the current circuit operating state data; Input the current circuit operating state data into the forget gate of the circuit operating state prediction model to determine the current circuit operating state data that needs to be discarded from the memory unit. The corresponding calculation formula is as follows: In the formula, represents the output of the forget gate at the current time t, which is used to determine the current circuit operating state data to be discarded from the memory unit; represents the activation function of the forget gate; represents the weight of the forget gate; represents the hidden state at the previous time t-1; represents the current circuit operating state data input at the current time t; represents the hidden state and the current circuit operating state data to form a vector; represents the bias term of the forget gate; Based on the input gate of the circuit operating state prediction model, determine the current circuit operating state data that needs to be stored in the memory unit. The corresponding calculation formula is as follows: In the formula, represents the output of the input gate at the current time t, which is used to determine the current circuit operating state data to be stored in the memory unit; represents the activation function of the input gate; represents the weight of the input gate; represents the hidden state at the previous time t - 1; represents the current circuit operating state data input at the current time t; represents the hidden state and the current circuit operating state data to form a vector; represents the bias term of the input gate; Based on the candidate memory cells of the circuit operating state prediction model, determine the predicted circuit operating state data. The corresponding calculation formula is as follows: In the formula, represents the candidate memory cell at the current moment t, which is used to determine the operation state data of the prediction circuit; represents the hyperbolic tangent function; represents the weight of the candidate memory cell; represents the hidden state at the previous moment t - 1; represents the current circuit operation state data input at the current moment t; represents the hidden state and the current circuit operation state data to form a vector; represents the bias term of the candidate memory cell; The calculation formula for updating the memory unit is as follows: In the formula, represents the cell state at the current time t; represents the output of the forget gate at the current time t; represents the cell state at the previous time t - 1; represents the output of the input gate at the current time t; represents the candidate cell state at the current time t; Based on the output gate of the circuit operating state prediction model, determine the predicted circuit operating state data that needs to be output to the hidden state. The corresponding calculation formula is as follows: In the formula, represents the output of the output gate at the current moment t, and is used to determine the predicted circuit operation state data that needs to be output to the hidden state; represents the activation function of the output gate; represents the output of the output gate; represents the hidden state at the previous moment t - 1; represents the current circuit operation state data input at the current moment t; represents the hidden state and the current circuit operation state data constitute a vector; represents the bias term of the output gate; According to the cell state at the current moment t and the output of the output gate, predict the future circuit operating state. The corresponding calculation formula is as follows: In the formula, represents the hidden state at the current time t, that is, the predicted future circuit operation state; represents the hyperbolic tangent function; represents the cell state at the current time t.

10. A deep fusion digital full-condition permanent magnet circuit breaker control method, applied to a deep fusion digital full-condition permanent magnet circuit breaker control system according to any one of claims 1-9, the method includes: Based on the switch body, collect the circuit breaker switch signal data through the switch state quantity port, collect the circuit voltage signal data through the voltage transformer, and collect the circuit current signal data through the current transformer; Summarize the circuit breaker switch signal data, the circuit voltage signal data, and the circuit current signal data to generate the circuit breaker analog signal data; Convert the circuit breaker analog signal data into circuit breaker digital signal data and transmit it to the digital feeder terminal; Based on the digital feeder terminal, monitor the circuit breaker switch state and identify the current circuit fault information according to the circuit breaker digital signal data; Build a prediction model for the operating state of the circuit, and predict the future operating state of the circuit based on the breaker switch state and the current circuit fault information.

Images