Defect analysis and early warning system and method for circuit breaker of alternating current filter bank

Abstract

The invention discloses an alternating current filter bank circuit breaker defect analysis early warning system and method, relates to the technical field of converter station alternating current filter circuit breakers, and solves the problem that the accuracy and the efficiency of circuit breaker defect judgment are limited due to relatively single monitoring means of an existing alternating current filter bank circuit breaker. The system comprises a central processing unit, a power conversion management unit, a communication unit, a data acquisition unit, an FPGA, a control screen and an early warning unit, the central processing unit performs instruction control on each unit module; the data acquisition unit acquires operation data of the circuit breaker in real time through a sensor; the FPGA is matched with the central processing unit, and performs early warning analysis on the circuit breaker by using a radial basis function neural network; and the early warning unit is used for carrying out early warning on the defects of the circuit breaker. The FPGA and the central processing unit work cooperatively to form a complete system, and the real-time performance, the high efficiency, the flexibility, the expandability, the accuracy and the low power consumption performance in circuit breaker defect early warning analysis are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of AC filter circuit breakers in converter stations, and in particular to an AC filter group circuit breaker defect analysis and early warning system and method. Background Art

[0002] At present, HVDC converter stations play a vital role in the composition of power networks. In particular, as the core equipment of DC transmission systems, their operational stability is directly related to the normal operation of the entire power network. AC filter banks, as an indispensable component of HVDC converter stations, their transient process monitoring, analysis and early warning technology are of irreplaceable importance in ensuring the stable and efficient operation of converter stations. With the continuous growth of electricity demand and the improvement of power grid construction, HVDC transmission technology has been widely used.

[0003] In the existing technology, the AC filter group is an important component of the high-voltage direct current transmission system. Its circuit breaker plays a key role in the power system, which can cut off the circuit when the current is abnormal, protecting the circuit and the filter group from damage.

[0004] However, in the prior art, the monitoring means for AC filter bank circuit breakers are relatively simple, which limits the accuracy and efficiency of judging circuit breaker defects. Summary of the Invention

[0005] The purpose of the present invention is to provide an AC filter bank circuit breaker defect analysis and early warning system and method, aiming to solve the technical problem that the monitoring means of AC filter bank circuit breakers in the prior art are relatively simple, which limits the accuracy and efficiency of circuit breaker defect judgment.

[0006] To achieve the above objectives, the present invention adopts an AC filter bank circuit breaker defect analysis and early warning system, comprising: a central processing unit, a power conversion management unit, a communication unit, a data acquisition unit, an FPGA, a control panel, and an early warning unit; the central processing unit is respectively connected to the power conversion management unit, the communication unit, the data acquisition unit, the FPGA, the control panel, and the early warning unit; The central processing unit is used to perform command control on the power conversion management unit, the communication unit, the data acquisition unit, the FPGA, the control panel and the early warning unit; The power conversion management unit is used to convert, process and distribute the system power; The communication unit is used to access wireless networks and wired networks to achieve wireless data transmission with external systems and devices; The data acquisition unit is used to collect the operating data of the circuit breaker in real time through sensors; The FPGA is used to cooperate with the central processing unit to perform early warning analysis on the circuit breaker using a radial basis function neural network; The control panel is used for the operator to interactively manage and control the early warning system; The early warning unit is used to issue an early warning alarm for defects of the circuit breaker.

[0007] The FPGA is used to provide parallel processing capabilities for the radial basis function neural network, accelerating the calculation speed. When using the radial basis function neural network to provide fault defect warnings for circuit breakers, feature quantities are first extracted, a training library is established based on historical data, the extracted feature quantities are modeled using the radial basis function neural network, and then the radial basis function neural network is learned and parameter identification is performed using a closing algorithm. When abnormal signs are extracted from the real-time opening and closing recording data, the radial basis function neural network can issue an alarm before the abnormality expands or causes adverse effects.

[0008] The feature quantities include time domain feature quantities and frequency domain feature quantities; The time domain characteristic quantities include the peak value, mean value and variance of the opening and closing currents, the opening time or closing time, the differential current at the beginning and end of the circuit breaker, the input value of the closing resistance, the maximum and minimum current values; The frequency domain characteristic quantities include harmonic maximum value, harmonic content and total harmonic distortion rate, and harmonic content of zero-sequence current.

[0009] Wherein, the data acquisition unit includes a current sensor, a voltage sensor, a temperature sensor, a vibration sensor, a gas pressure sensor and a mechanical position sensor; The current sensor is used to monitor the magnitude and direction of the current passing through the circuit breaker; The voltage sensor is used to monitor the voltage value at both ends of the circuit breaker; The temperature sensor is used to monitor the heat generated by the circuit breaker during operation and monitor temperature changes in real time; The vibration sensor is used to monitor the vibration amplitude of the circuit breaker during operation; The gas pressure sensor is used to monitor the pressure of the gas inside the circuit breaker; The mechanical position sensor is used to monitor the opening and closing conditions of the circuit breaker.

[0010] Wherein, the warning unit includes a flashing light and a buzzer; The flashing light is used to provide a visual warning by flashing lights of different colors alternately; The buzzer is used to provide auditory warning by emitting sounds of different frequencies and volumes.

[0011] Wherein, the communication unit includes an RJ-45 interface, a transmitter, a receiver, an antenna, a filter and a controller; The RJ-45 interface is used for wired connection via an RJ-45 plug; The transmitter is used to convert the information to be sent into a signal form suitable for wireless transmission; The receiver is used to receive the wireless signal received from the transmission medium and convert it into a usable information form; The antenna is used to convert the electromagnetic waves generated by the transmitter into wireless signals and radiate them into space; and to receive the wireless signals received in space and convert them into signals that can be processed by the receiver.

[0012] The present invention further provides an AC filter bank circuit breaker defect analysis and early warning method, which is applied to the AC filter bank circuit breaker defect analysis and early warning system as described above, and comprises the following steps: The power supply is connected to the circuit breaker defect analysis and early warning system through the power conversion management unit, and the data acquisition unit monitors various data in the circuit breaker in real time; The real-time data of the circuit breaker is transmitted to the FPGA through the central processing unit; The central processing unit and the FPGA perform early warning analysis on the monitoring data using a radial basis function neural network; Generate early warning signals based on the output results of the radial basis function neural network model; The warning signal of the output result is transmitted back to the central processing unit, and the central processing unit controls the communication unit and the warning unit to issue a warning prompt.

[0013] The beneficial effects of the present invention are as follows: the present invention utilizes FPGA and a central processing unit to implement a radial basis function neural network for early warning analysis of circuit breaker defects. The parallel processing capability of the FPGA enables the radial basis function neural network to execute quickly, meeting real-time requirements. It has the effects of real-time, high efficiency, flexibility, scalability, accuracy, and low power consumption in early warning analysis of circuit breaker defects. At the same time, the FPGA can implement hardware acceleration of the radial basis function neural network, convert the algorithm into a hardware description language and implement it on the FPGA, thereby greatly improving processing speed and efficiency. The FPGA and the central processing unit work together to form a complete system. The FPGA is responsible for real-time data processing and accelerated computing, while the central processing unit is responsible for logical control and high-level decision-making, so as to obtain the best early warning effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 The present invention is a schematic structural diagram of an AC filter group circuit breaker defect analysis and early warning system.

[0016] Figure 2 It is a system diagram of the data acquisition unit of the present invention.

[0017] Figure 3 is a system diagram of the communication unit of the present invention.

[0018] Figure 4 It is a system diagram of the power conversion management unit of the present invention.

[0019] Figure 5 It is a system diagram of the protection module of the present invention.

[0020] Figure 6 It is a system diagram of the early warning unit of the present invention.

[0021] Figure 7 The present invention is a flowchart of the steps of an AC filter group circuit breaker defect analysis and early warning method.

[0022] Illustration: 1-Central processing unit, 2-Power conversion management unit, 3-Communication unit, 4-Data acquisition unit, 5-FPGA, 6-Control panel, 7-Early warning unit, 8-Current sensor, 9-Voltage sensor, 10-Temperature sensor, 11-Vibration sensor, 12-Gas pressure sensor, 13-Mechanical position sensor, 14-Strobe light, 15-Buzzer, 16-RJ-45 interface, 17-Transmitter, 18-Receiver, 19-Antenna, 20-Filter, 21-Controller, 22-Power regulator, 23-Power controller, 24-Power conversion circuit, 25-Protection module, 26-Overvoltage protection circuit, 27-Overcurrent protection circuit, 28-Short circuit protection circuit. DETAILED DESCRIPTION

[0024] See also Figures 1 to 6An embodiment of the present invention provides an AC filter group circuit breaker defect analysis and early warning system, including a central processing unit 1, a power conversion management unit 2, a communication unit 3, a data acquisition unit 4, an FPGA 5, a control panel 6 and an early warning unit 7; the central processing unit 1 is respectively connected to the power conversion management unit 2, the communication unit 3, the data acquisition unit 4, the FPGA 5, the control panel 6 and the early warning unit 7.

[0025] The central processing unit 1 is used to issue instructions to the power conversion management unit 2, communication unit 3, data acquisition unit 4, FPGA5, control panel 6 and early warning unit 7; the power conversion management unit 2 is used to convert, process and distribute the system power; the communication unit 3 is used to access wireless networks and wired networks to realize wireless data transmission with external systems and equipment; the data acquisition unit 4 is used to collect the operating data of the circuit breaker in real time through sensors; the FPGA5 is used to cooperate with the central processing unit 1 to use the radial basis function neural network to perform early warning analysis on the circuit breaker; the control panel 6 is used for the operator to interact with the early warning system for management and control; the early warning unit 7 is used to issue early warning alarms for defects in the circuit breaker.

[0026] In this embodiment, a radial basis function neural network is implemented using FPGA 5 and central processing unit 1 to perform early warning analysis of circuit breaker defects. The parallel processing capability of FPGA 5 enables the rapid execution of the radial basis function neural network, meeting real-time requirements. This provides real-time, high-efficiency, flexibility, scalability, accuracy, and low power consumption in early warning analysis of circuit breaker defects. Furthermore, FPGA 5 can implement hardware acceleration of the radial basis function neural network, converting the algorithm into a hardware description language and implementing it on FPGA 5, thereby significantly improving processing speed and efficiency. The FPGA 5 and central processing unit 1 work together to form a complete system. FPGA 5 is responsible for real-time data processing and accelerated computing, while central processing unit 1 is responsible for logical control and high-level decision-making, to achieve the best early warning effect. When calculating the radial basis function neural network, for each input sample Xi, the output of the hidden layer neuron j can be calculated by substituting the distance between the input sample and the center point into the radial basis function, that is; represents the response of the hidden layer neuron j to the input sample Xi; represents the center point vector of the jth hidden layer neuron.

[0027] The output layer of the radial basis function neural network is a linear combination of the outputs of the hidden layer neurons. Specifically, if the hidden layer has h neurons, the output of the output layer neurons can be expressed as; where is the weight from hidden layer neuron j to output layer neuron k, and is the response of hidden layer neuron j to output layer neuron k.

[0028] Furthermore, FPGA5 provides parallel processing capabilities for the radial basis function neural network, accelerating the calculation speed. When using the radial basis function neural network to provide fault defect warnings for circuit breakers, feature quantities are first extracted, a training library is established based on historical data, the extracted feature quantities are modeled through the radial basis function neural network, and then the radial basis function neural network is learned and parameter identification is performed using the network closing algorithm. When abnormal signs are extracted from the real-time opening and closing recording data, the network can issue an alarm before the abnormality expands or causes adverse effects.

[0029] In this embodiment, the radial basis function neural network has a simple structure, is more intuitive and easy to understand in design and training, has strong approximation ability, can handle complex nonlinear problems, can perform well in a variety of application scenarios, has fast learning convergence speed, strong generalization ability, and local response characteristics, which makes the radial basis function neural network more efficient in processing high-dimensional data.

[0030] Furthermore, the feature quantity includes a time domain feature quantity and a frequency domain feature quantity; Time domain characteristics include the peak value, mean value and variance of the opening and closing current, the opening time or closing time, the differential current at the beginning and end of the circuit breaker, the input value of the closing resistor, and the maximum and minimum current values; Frequency domain characteristics include harmonic maximum value, harmonic content and total harmonic distortion rate, and harmonic content of zero-sequence current.

[0031] In this embodiment, time domain features and frequency domain features are extracted to analyze the dynamic characteristics, frequency components, and key information of energy distribution of the signal, thereby deeply understanding the nature and behavior of the signal.

[0032] Furthermore, the data acquisition unit 4 includes a current sensor 8, a voltage sensor 9, a temperature sensor 10, a vibration sensor 11, a gas pressure sensor 12 and a mechanical position sensor 13; the current sensor 8 is used to monitor the current size and direction passing through the circuit breaker; the voltage sensor 9 is used to monitor the voltage value at both ends of the circuit breaker; the temperature sensor 10 is used to monitor the heat generated by the circuit breaker during operation and monitor the temperature changes in real time; the vibration sensor 11 is used to monitor the vibration amplitude of the circuit breaker during operation; the gas pressure sensor 12 is used to monitor the pressure of the gas inside the circuit breaker; and the mechanical position sensor 13 is used to monitor the opening and closing conditions of the circuit breaker.

[0033] In this embodiment, multiple data characteristics of the circuit breaker are monitored in real time, including the current, voltage, and temperature data of the circuit breaker, as well as the vibration frequency and mechanical displacement data of the circuit breaker to ensure stable operation of the circuit breaker. The internal gas pressure of the circuit breaker is monitored in real time to monitor the operating status of the circuit breaker. The real-time monitoring of multiple data of the circuit breaker by multiple sensors can make the defect analysis of the circuit breaker more real-time and accurate.

[0034] Furthermore, the warning unit 7 includes a flashing light 14 and a buzzer 15; the flashing light 14 produces a strong visual impact for visual warning by flashing lights of different colors alternately; the buzzer 15 produces a strong auditory impact for warning by emitting sounds of different frequencies and volumes.

[0035] In this embodiment, the visual and auditory impact warning is achieved by the flashing light 14 and the buzzer 15, which can provide early warning information to the staff in a timely and effective manner, thereby achieving a rapid early warning response.

[0036] Furthermore, the communication unit 3 includes an RJ-45 interface 16, a transmitter 17, a receiver 18, an antenna 19, a filter 20 and a controller 21; the RJ-45 interface 16 is used for wired connection through an RJ-45 plug; the transmitter 17 is responsible for converting the information to be sent into a signal form suitable for wireless transmission; the receiver 18 is responsible for receiving the wireless signal received from the transmission medium and converting it into a usable information form; the antenna 19 is responsible for converting the electromagnetic waves generated by the transmitter 17 into wireless signals and radiating them into space, and is also responsible for receiving the wireless signals received in space and converting them into signals that can be processed by the receiver 18.

[0037] In this embodiment, a wired connection to the network is achieved through the RJ-45 interface 16, and the input and received data are filtered and controlled by the filter 20 and the controller 21. At the same time, wireless data content can be transmitted and received through the antenna 19, the transmitter 17 and the receiver 18, thereby achieving the purpose of wireless connection.

[0038] Furthermore, the power conversion management unit 2 includes a power regulator 22, a power controller 23, a power conversion circuit 24 and a protection module 25; the power regulator 22 is responsible for converting the input voltage into the stable output voltage required by the device; the power controller 23 is responsible for monitoring and controlling the voltage, current and power parameters; the power conversion circuit 24 converts AC power into DC power, and converts DC power into different voltages or different currents; the protection module 25 protects the circuit breaker defect analysis and early warning system to prevent power failures from damaging the circuit breaker defect analysis and early warning system.

[0039] In this embodiment, the power regulator 22 regulates and controls the voltage, and the power controller 23 is responsible for real-time monitoring of the output voltage of the power regulator 22 to ensure the stability of its voltage and current output. The power conversion circuit 24 converts the input voltage according to the voltage required by different devices to make it suitable for the entire early warning system, and the protection module 25 protects the power input. When necessary, the early warning system can be protected by cutting off the power supply.

[0040] Furthermore, the protection module 25 includes an overvoltage protection circuit 26, an overcurrent protection circuit 27 and a short-circuit protection circuit 28; the overvoltage protection circuit 26 is used to prevent the voltage from exceeding the maximum tolerance of the device, thereby avoiding damage to sensitive electronic components; the overcurrent protection circuit 27 is used to prevent the current from exceeding the safe carrying capacity of the device or circuit; the short-circuit protection circuit 28 is used to prevent short circuits in the circuit, and can cut off the power supply when a short circuit occurs to avoid serious damage.

[0041] In this embodiment, the voltage, current and short circuit of the input power supply are monitored by the overvoltage protection circuit 26, the overcurrent protection circuit 27 and the short circuit protection circuit 28. When any of the current is too large or too low, the voltage is too large or too low, or a short circuit occurs in the circuit, the power circuit is cut off. By cutting off the power circuit, the entire early warning system is protected to prevent components from being burned under abnormal conditions.

[0042] See also Figure 7 The embodiment of the present invention further provides an AC filter bank circuit breaker defect analysis and early warning method, which is applied to the AC filter bank circuit breaker defect analysis and early warning system as described above, and includes the following steps: S1: The power supply is connected to the circuit breaker defect analysis and early warning system through the power conversion management unit 2, and the data acquisition unit 4 monitors the various data in the circuit breaker in real time; S2: The real-time data of the circuit breaker is transmitted to the FPGA 5 through the central processor 1; S3: The central processing unit 1 and FPGA 5 perform early warning analysis on the monitoring data using a radial basis function neural network; S4: Generate an early warning signal based on the output results of the radial basis function neural network model; S5: The warning signal of the output result is transmitted back to the central processing unit 1, and the central processing unit 1 controls the communication unit 3 and the warning unit 7 to issue a warning prompt.

[0043] In this embodiment, FPGA5 can implement hardware acceleration of the radial basis function neural network, convert the algorithm into a hardware description language and implement it on FPGA5, thereby significantly improving processing speed and efficiency. The FPGA5 and the central processor 1 work together to form a complete system, improving the real-time, high efficiency, flexibility, scalability, accuracy and low power consumption of circuit breaker defect warning analysis.

[0044] The above disclosure is only a preferred embodiment of the present invention, and certainly cannot be used to limit the scope of the rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made in accordance with the claims of the present invention are still within the scope of the invention.

Claims

1. An AC filter bank circuit breaker defect analysis and early warning system, characterized in that: include: Central processing unit, power conversion management unit, communication unit, data acquisition unit, FPGA, control panel and early warning unit; The central processing unit is respectively connected to the power conversion management unit, the communication unit, the data acquisition unit, the FPGA, the control screen and the early warning unit; The central processing unit is used to perform command control on the power conversion management unit, the communication unit, the data acquisition unit, the FPGA, the control panel and the early warning unit; The power conversion management unit is used to convert, process and distribute the system power; The communication unit is used to access wireless networks and wired networks to achieve wireless data transmission with external systems and devices; The data acquisition unit is used to collect the operating data of the circuit breaker in real time through sensors; The FPGA is used to cooperate with the central processing unit to perform early warning analysis on the circuit breaker using a radial basis function neural network; The control panel is used for the operator to interactively manage and control the early warning system; The early warning unit is used to issue an early warning alarm for defects of the circuit breaker.

2. The AC filter bank circuit breaker defect analysis and early warning system according to claim 1, characterized in that: The FPGA is used to provide parallel processing capabilities for the radial basis function neural network, thereby accelerating the calculation speed. When using the radial basis function neural network to provide fault defect warnings for circuit breakers, feature quantities are first extracted, a training library is established based on historical data, the extracted feature quantities are modeled using the radial basis function neural network, and then a network closing algorithm is used to learn and identify parameters of the radial basis function neural network. When abnormal signs are extracted from the real-time opening and closing recording data, the radial basis function neural network can issue an alarm before the abnormality expands or causes adverse effects.

3. The AC filter bank circuit breaker defect analysis and early warning system according to claim 2, characterized in that: The feature quantities include time domain feature quantities and frequency domain feature quantities; The time domain characteristic quantities include the peak value, mean value and variance of the opening and closing currents, the opening time or closing time, the differential current at the beginning and end of the circuit breaker, the input value of the closing resistance, the maximum and minimum current values; The frequency domain characteristic quantities include harmonic maximum value, harmonic content and total harmonic distortion rate, and harmonic content of zero-sequence current.

4. The AC filter bank circuit breaker defect analysis and early warning system according to claim 1, characterized in that: The data acquisition unit includes a current sensor, a voltage sensor, a temperature sensor, a vibration sensor, a gas pressure sensor and a mechanical position sensor; The current sensor is used to monitor the magnitude and direction of the current passing through the circuit breaker; The voltage sensor is used to monitor the voltage value at both ends of the circuit breaker; The temperature sensor is used to monitor the heat generated by the circuit breaker during operation and monitor temperature changes in real time; The vibration sensor is used to monitor the vibration amplitude of the circuit breaker during operation; The gas pressure sensor is used to monitor the pressure of the gas inside the circuit breaker; The mechanical position sensor is used to monitor the opening and closing conditions of the circuit breaker.

5. The AC filter bank circuit breaker defect analysis and early warning system according to claim 1, characterized in that: The early warning unit includes a flashing light and a buzzer; The flashing light is used to provide a visual warning by flashing lights of different colors alternately; The buzzer is used to provide auditory warning by emitting sounds of different frequencies and volumes.

6. The AC filter bank circuit breaker defect analysis and early warning system according to claim 1, characterized in that: The communication unit includes an RJ-45 interface, a transmitter, a receiver, an antenna, a filter and a controller; The RJ-45 interface is used for wired connection via an RJ-45 plug; The transmitter is used to convert the information to be sent into a signal form suitable for wireless transmission; The receiver is used to receive the wireless signal received from the transmission medium and convert it into a usable information form; The antenna is used to convert the electromagnetic waves generated by the transmitter into wireless signals and radiate them into space; and to receive the wireless signals received in space and convert them into signals that can be processed by the receiver.

7. A method for analyzing and warning defects of an AC filter bank circuit breaker, applied to an AC filter bank circuit breaker defect analysis and warning system according to any one of claims 1 to 6, characterized in that: The steps include: The power supply is connected to the circuit breaker defect analysis and early warning system through the power conversion management unit, and the data acquisition unit monitors various data in the circuit breaker in real time; The real-time data of the circuit breaker is transmitted to the FPGA through the central processing unit; The central processing unit and the FPGA perform early warning analysis on the monitoring data using a radial basis function neural network; Generate early warning signals based on the output results of the radial basis function neural network model; The warning signal of the output result is transmitted back to the central processing unit, and the central processing unit controls the communication unit and the warning unit to issue a warning prompt.

Images