State monitoring system and converter valve

Abstract

The invention relates to a state monitoring system and a converter valve. The system comprises a voltage-sharing capacitor, an electrical parameter measuring circuit and a monitoring system platform, wherein the electrical parameter measuring circuit is respectively connected with the voltage-sharing capacitor and the monitoring system platform; the electrical parameter measuring circuit is used for measuring electrical parameters of the voltage-sharing capacitor and sending the electrical parameters to the monitoring system platform; the electrical parameters comprise a voltage parameter and a current parameter, and the current parameter is measured by an optical current sensor; and the monitoring system platform is used for analyzing the electrical parameters, determining the current state of the voltage-sharing capacitor, and outputting early warning prompt information when the current state is an abnormal state. The invention provides a state monitoring system capable of carrying out real-time online monitoring on the state of a voltage-sharing capacitor, and online monitoring and early warning can be realized when the voltage-sharing capacitor is in a working state through an electrical parameter measuring circuit and a monitoring system platform; and the real-time performance and the detection efficiency of the performance detection of the voltage-sharing capacitor are improved.

Description

Technical Field

[0001] The present application relates to the technical field of converter valves, and particularly to a state monitoring system and a converter valve. Background Art

[0002] A converter valve is composed of components such as thyristors, damping capacitors, voltage-sharing capacitors, damping resistors, voltage-sharing resistors, saturable reactors, and thyristor control modules, and can realize the regulation of voltage and power in a DC power transmission system. Among them, the voltage-sharing capacitors in the converter valve can balance the voltages on both sides of the converter valve and ensure the normal operation of the thyristor converter valve. Therefore, the performance of the voltage-sharing capacitors is crucial.

[0003] Traditionally, the performance detection of the voltage-sharing capacitors in a converter valve is mainly carried out in an offline state and requires manual participation, resulting in poor real-time performance and low detection efficiency of the voltage-sharing capacitor performance detection. Summary of the Invention

[0004] Based on this, it is necessary to provide a state monitoring system and a converter valve that can perform online performance monitoring on the voltage-sharing capacitors in the converter valve and improve the real-time performance and detection efficiency of the voltage-sharing capacitor performance detection for the above technical problems.

[0005] In a first aspect, the present application provides a state monitoring system, including: a voltage-sharing capacitor, an electrical parameter measurement circuit, and a monitoring system platform, where the electrical parameter measurement circuit is respectively connected to the voltage-sharing capacitor and the monitoring system platform;

[0006] The electrical parameter measurement circuit is configured to measure the electrical parameters of the voltage-sharing capacitor and send the electrical parameters to the monitoring system platform; the electrical parameters include voltage parameters and current parameters, and the current parameters are measured by an optical current sensor;

[0007] The monitoring system platform is configured to analyze the electrical parameters, determine the current state of the voltage-sharing capacitor, and output a warning prompt message when the current state is an abnormal state.

[0008] In one embodiment, the electrical parameter measurement circuit includes a voltage measurement module, a current measurement module, and a comprehensive processing module. The input end of the voltage measurement module is connected to both ends of the voltage-sharing capacitor, the output end of the voltage measurement module is connected to the comprehensive processing module through a wire, the input end of the current measurement module is connected to the output branch of the voltage-sharing capacitor, and the output end of the current measurement module is connected to the comprehensive processing module through a first optical fiber;

[0009] The voltage measurement module is configured to measure the voltage parameters of the voltage-sharing capacitor and transmit the voltage electrical signal carrying the voltage parameters to the comprehensive processing module through a wire;

[0010] A current measurement module is used to measure the current parameters of the voltage-sharing capacitor and transmit the current optical signal carrying the current parameters to the comprehensive processing module through the first optical fiber; the current measurement module includes an optical current sensor.

[0011] The comprehensive processing module is used to obtain voltage parameters from the voltage electrical signal and current parameters from the current optical signal, and send the voltage parameters and current parameters to the monitoring system platform.

[0012] In one embodiment, the optical current sensor includes a light source, an optical signal conversion module, a second optical fiber, an optical signal splitting module, and a signal processing module. The second optical fiber is wound around the output branch of the voltage-sharing capacitor.

[0013] The initial optical signal emitted by the light source is subjected to polarization state conversion processing by the optical signal conversion module to form a linearly polarized light. The linearly polarized light enters the second optical fiber. Under the action of the magnetic field generated by the current in the output branch, the polarization plane of the linearly polarized light rotates. The rotated linearly polarized light forms a first linearly polarized light and a second linearly polarized light perpendicular to each other after passing through the optical signal splitting module. The signal processing module analyzes and processes the first linearly polarized light and the second linearly polarized light to generate a current optical signal carrying the current parameters.

[0014] In one embodiment, the comprehensive processing module includes an electro-optic converter, an optical fiber receiver, and a data processor. The electro-optic converter is respectively connected to the voltage measurement module and the data processor, and the optical fiber receiver is respectively connected to the optical current sensor and the data processor.

[0015] The electro-optic converter is used to convert the voltage electrical signal to obtain a voltage optical signal and transmit the voltage optical signal to the data processor.

[0016] The optical fiber receiver is used to receive the current optical signal and transmit the current optical signal to the data processor.

[0017] The data processor is used to obtain voltage parameters from the voltage optical signal and current parameters from the current optical signal.

[0018] In one embodiment, the system further includes: a laser power supply circuit, and the laser power supply circuit is connected to the electrical parameter measurement circuit.

[0019] The laser power supply circuit is used to supply electrical energy to the electrical parameter measurement circuit.

[0020] In one embodiment, the monitoring system platform includes an edge computing module, a depth analysis module, and an early warning module.

[0021] The edge computing module is used to perform difference analysis on the voltage parameters and current parameters respectively according to the standard parameter library, and determine whether the voltage-sharing capacitor is in an abnormal state according to the difference analysis result.

[0022] A depth analysis module, configured to input voltage parameters and current parameters into a preset depth analysis model to determine the type of abnormal state when the voltage equalizing capacitor is in an abnormal state;

[0023] An early warning module, configured to output corresponding early warning prompt information according to the type of abnormal state.

[0024] In one embodiment, the standard parameter library includes at least one standard voltage waveform and at least one standard current waveform. According to the standard parameter library, difference analysis is respectively performed on the voltage parameters and the current parameters, and it is determined whether the voltage equalizing capacitor is in an abnormal state according to the difference analysis results, including:

[0025] Determine the actual voltage waveform according to the voltage parameters, and determine the actual current waveform according to the current parameters;

[0026] Perform difference analysis on the actual voltage waveform and at least one standard voltage waveform respectively to obtain at least one voltage difference;

[0027] Perform difference analysis on the actual current waveform and at least one standard current waveform respectively to obtain at least one current difference;

[0028] If there is at least one voltage difference greater than the preset voltage difference threshold, or there is at least one current difference greater than the preset current difference threshold, it is determined that the voltage equalizing capacitor is in an abnormal state.

[0029] In one embodiment, inputting the voltage parameters and the current parameters into a preset depth analysis model to determine the type of abnormal state includes:

[0030] Determine the actual voltage waveform according to the voltage parameters, and determine the actual current waveform according to the current parameters;

[0031] Input the actual voltage waveform and the actual current waveform into a preset depth analysis model to determine the type of abnormal state.

[0032] In one embodiment, inputting the actual voltage waveform and the actual current waveform into a preset depth analysis model to determine the type of abnormal state includes:

[0033] Denoise the actual voltage waveform and the actual current waveform to obtain a denoised voltage waveform and a denoised current waveform;

[0034] Normalize the denoised voltage waveform according to the preset voltage characteristics of the denoised voltage waveform to obtain a normalized voltage waveform;

[0035] Normalize the denoised current waveform according to the preset current characteristics of the denoised current waveform to obtain a normalized current waveform;

[0036] Input the normalized voltage waveform and the normalized current waveform into a preset in-depth analysis model to determine the type of abnormal state.

[0037] In a second aspect, the present application also provides a commutation valve, including: a recovery period protection module, a grading capacitor, and an electrical parameter measurement circuit. The grading capacitor is connected in series with the output end of the recovery period protection module, and the electrical parameter measurement circuit is connected to the grading capacitor;

[0038] The electrical parameter measurement circuit is configured to measure the electrical parameters of the grading capacitor and send the electrical parameters to the monitoring system platform. The electrical parameters are used to instruct the monitoring system platform to analyze the electrical parameters, determine the current state of the grading capacitor, and output a warning prompt message when the current state is an abnormal state.

[0039] The above state monitoring system and commutation valve, wherein the state monitoring system includes a grading capacitor, an electrical parameter measurement circuit, and a monitoring system platform. The electrical parameter measurement circuit is respectively connected to the grading capacitor and the monitoring system platform; wherein, the electrical parameter measurement circuit is configured to measure the electrical parameters of the grading capacitor and send the electrical parameters to the monitoring system platform; the electrical parameters include voltage parameters and current parameters, and the current parameters are measured by an optical current sensor; the monitoring system platform is configured to analyze the electrical parameters, determine the current state of the grading capacitor, and output a warning prompt message when the current state is an abnormal state. That is, the embodiment of the present application proposes a state monitoring system capable of performing real-time online monitoring on the state of the grading capacitor. In this system, an electrical parameter measurement circuit for performing real-time online measurement of the electrical parameters of the grading capacitor is provided, and a corresponding monitoring system platform is provided, so that when the grading capacitor is in a working state, the current electrical parameters of the grading capacitor can be measured, and the current state of the grading capacitor can be analyzed and determined based on the current electrical parameters. The current state of the grading capacitor can reflect the actual performance of the grading capacitor, so that when it is determined that the grading capacitor is abnormal, a warning prompt message can be output in a timely manner to achieve online monitoring and warning; it can not only improve the real-time performance of the grading capacitor performance detection, but also improve the detection efficiency of the grading capacitor performance detection, and improve the abnormal warning rate of the grading capacitor. Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1Schematic diagram of the state monitoring system provided by the embodiment of the present application;

[0042] Figure 2 Schematic diagram of the electrical parameter measurement circuit provided by the embodiment of the present application;

[0043] Figure 3 Schematic diagram of the optical current sensor provided by the embodiment of the present application;

[0044] Figure 4 Another schematic diagram of the electrical parameter measurement circuit provided by the embodiment of the present application;

[0045] Figure 5 Another schematic diagram of the state monitoring system provided by the embodiment of the present application;

[0046] Figure 6 Schematic diagram of the laser power supply circuit provided by the embodiment of the present application;

[0047] Figure 7 Schematic diagram of the monitoring system platform provided by the embodiment of the present application;

[0048] Figure 8 Schematic diagram of the training process of the deep learning model provided by the embodiment of the present application;

[0049] Figure 9 Complete schematic diagram of the state monitoring system for the grading capacitor in the converter valve provided by the embodiment of the present application;

[0050] Figure 10 Schematic diagram of the converter valve provided by the embodiment of the present application. Detailed implementation manners

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0052] The converter valve is composed of components such as thyristors, damping capacitors, grading capacitors, damping resistors, grading resistors, saturable reactors, and thyristor control modules, and can realize the regulation of voltage and power in the DC transmission system. Among them, the grading capacitor in the converter valve can balance the voltages on both sides of the converter valve and ensure the normal operation of the thyristor converter valve. Therefore, the performance of the grading capacitor is crucial.

[0053] Currently, the common detection methods for the grading capacitor connected in series with the recovery period unit (RPU) in the converter valve are as follows:

[0054] 1. Direct testing method

[0055] The direct test method is one of the common ways to detect the grading capacitors of the converter valve. It mainly uses tools such as multimeters and bridges to directly measure the grading capacitors. However, this method has many drawbacks. Before operation, the original circuit must be removed, and then each grading capacitor is measured one by one. This process not only takes a lot of time and has very low test efficiency, but also when reconnecting the circuit after the measurement, it is very easy to have problems with the contact resistance of the joints exceeding the standard, thus posing serious safety hazards. For example, if the contact resistance is too large, it may cause local overheating, damage the equipment, and even affect the stable operation of the entire converter valve system.

[0056] 2. Back-to-back test method

[0057] The back-to-back test method is a means to detect the grading capacitors in the converter valve. Its principle is to simulate as realistically as possible the working conditions faced by the grading capacitors during actual operation to accurately judge the capacitor performance. However, this method has significant defects. When the number of tested grading capacitors gradually increases, to meet the test requirements, the required capacity of the test will increase sharply in the same proportion. This means that more equipment and energy need to be invested, which not only lengthens the test cycle and greatly reduces the overall test efficiency, but also causes the economic cost to soar. In large-scale converter valve grading capacitor detection projects, these drawbacks are particularly prominent, greatly limiting the application scope of this method.

[0058] 3. Dielectric loss angle (D) test method

[0059] The tester uses professional measuring instruments such as dielectric loss measuring instruments to accurately measure the dielectric loss angle of the capacitor at a specified specific frequency to evaluate the quality of the capacitor insulation medium. Normally, for a capacitor with a smaller dielectric loss angle, its dielectric loss should be at a lower level, indicating better insulation performance. However, this method has certain limitations. First, it has strict requirements for equipment and frequency. Special dielectric loss measuring instruments must be used and the specific frequency must be accurately set, and the operation process is relatively complicated; second, the measurement results are easily affected by factors such as the accuracy and stability of the instrument itself; finally, this method can only focus on the dielectric loss index and cannot intuitively present the dynamic change of the capacitor capacity, and the evaluation of the overall capacitor performance is not comprehensive enough.

[0060] Although the traditional common detection methods for the grading capacitors in series on the RPU board of the converter valve play an important role in the safe operation of the high-voltage DC power system, there are still many problems in the existing technology and it is difficult to meet the requirements of the increasingly complex power system for monitoring the grading capacitors in series on the RPU board of the converter valve. Among them, the main problems include:

[0061] 1) The real-time and accuracy of data analysis are not high: The traditional data analysis methods described above all rely on offline processing, and simple threshold judgments are made through manual on-site handheld instruments, which makes it difficult to capture the real-time dynamic changes of the voltage-sharing capacitor during operation. This method not only consumes a lot of manpower and time, but also greatly limits the real-time and accurate grasp of the voltage-sharing capacitor of the converter valve, burying hidden dangers for the stable operation of the power system.

[0062] 2) Detection efficiency needs to be improved: Taking the back-to-back test method as an example, as the number of equalizing capacitors to be tested increases, the required test capacity will increase significantly, making the test process extremely cumbersome and time-consuming. The labor cost also rises sharply, which is far from keeping up with the pace of large-scale rapid detection of converter valves. It is urgent to optimize and innovate the existing process to significantly improve the detection efficiency.

[0063] 3) Operational convenience needs to be improved: The traditional direct testing method requires the original circuit to be dismantled first, and then the voltage-equalizing capacitors are measured one by one. The wiring process is complicated, and when the circuit is restored, the risk of excessive contact resistance of the connector is extremely high, which can cause safety hazards if not handled with care. This requires high professional skills of the operator, and it is urgent to simplify the operation process, lower the operating threshold, and make the detection work more convenient and efficient.

[0064] 4) Comprehensiveness of testing needs to be improved: Some current testing methods have obvious shortcomings. For example, when testers use dielectric loss meters to measure dielectric loss angles, although they can evaluate the performance of insulating media, they are limited to reflecting dielectric loss conditions and have no idea whether the capacitance has changed. It is difficult to make an accurate judgment on the overall performance of the capacitor. Therefore, it is imperative to develop a comprehensive testing method that can fully obtain all information about capacitors.

[0065] Based on this, the embodiment of the present application proposes a new online monitoring method for the voltage-equalizing capacitor of the converter valve RPU board, which collects and extracts the voltage at both ends of the voltage-equalizing capacitor and the current of the branch where it is located, and then performs signal conversion respectively, so as to realize real-time and accurate collection of the voltage / current data of the voltage-equalizing capacitor, upload it to the monitoring system platform after data aggregation, and combine it with advanced technologies such as early warning models and edge computing to build a multivariate data analysis system, which effectively solves the problems of low real-time and accuracy of data analysis, insufficient adaptive ability of early warning models, and low detection efficiency. This method can not only significantly improve the early warning capability of electrical attenuation of the voltage-equalizing capacitor, but also greatly enhance the reliability and interpretability of the early warning results, providing a more powerful guarantee for the safe operation of the power system.

[0066] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. These several specific embodiments below can be combined with each other, and for the same or similar concepts or processes, they may not be repeated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0067] Figure 1 It is a schematic structural diagram of the state monitoring system provided by the embodiment of this application. As Figure 1 shown, the state monitoring system 10 includes: a voltage-sharing capacitor 11, an electrical parameter measurement circuit 12, and a monitoring system platform 13. The electrical parameter measurement circuit 12 is connected to the voltage-sharing capacitor 11 and the monitoring system platform 13; among them,

[0068] The electrical parameter measurement circuit is used to measure the electrical parameters of the voltage-sharing capacitor and send the electrical parameters to the monitoring system platform; the electrical parameters include voltage parameters and current parameters, and the current parameters are measured by an optical current sensor;

[0069] The monitoring system platform is used to analyze the electrical parameters, determine the current state of the voltage-sharing capacitor, and output a warning prompt message when the current state is an abnormal state.

[0070] Exemplarily, the voltage-sharing capacitor 11 can be an electrical component in a converter valve, and it can be connected in series with a recovery period protection module (Recovery Period Unit, RPU) in the converter valve. For example, at least one voltage-sharing capacitor is connected in series at the output end of the RPU board to achieve voltage sharing protection for the RPU board. Of course, this voltage-sharing capacitor can also be an electrical component in other electrical devices other than the converter valve. That is to say, the state monitoring system for the voltage-sharing capacitor proposed in the embodiment of this application can be applied to all electrical devices, so as to realize online state monitoring of the voltage-sharing capacitor in the electrical device.

[0071] Exemplarily, when performing on-line status monitoring on the voltage-sharing capacitor 11, the electrical parameter measurement circuit 12 connected to the voltage-sharing capacitor 11 can be used to collect the electrical parameters of the voltage-sharing capacitor 11 in real time, including but not limited to the voltage parameter across the voltage-sharing capacitor 11 and the current parameter flowing through the voltage-sharing capacitor 11. That is to say, the electrical parameter measurement circuit 12 can be used to perform real-time on-line measurement of the electrical parameters of the voltage-sharing capacitor 11, so as to obtain the voltage parameter and current parameter of the voltage-sharing capacitor 11, such as the real-time voltage value and real-time current value. On this basis, the electrical parameter measurement circuit 12 can also upload the measured voltage parameter and current parameter of the voltage-sharing capacitor 11 to the monitoring system platform 13 in real time through the network. Exemplarily, the electrical parameter measurement circuit 12 can be connected to the monitoring system platform 13 through a wired network or a wireless network. The monitoring system platform 13 can be a local service platform, a remote service platform, or a cloud service platform, etc.; the type of the monitoring system platform is not specifically limited in the embodiments of the present application.

[0072] Exemplarily, for the electrical parameter measurement circuit 12, it can include a voltage measurement module and a current measurement module. Among them, the voltage measurement module can be connected to both ends of the voltage-sharing capacitor 11 and is used to measure the voltage parameter of the voltage-sharing capacitor 11; the current measurement module can be connected to the input / output branch of the voltage-sharing capacitor 11 and is used to measure the current parameter of the voltage-sharing capacitor 11. The voltage measurement module can select corresponding voltage measurement elements according to different voltage measurement principles to form different voltage measurement modules, and the current measurement module can also select corresponding current measurement elements according to different current measurement principles to form different current measurement modules. The specific principles and circuit structures of the voltage measurement module and the current measurement module are not specifically limited in this example.

[0073] Exemplarily, for the current measurement module, it can use an optical current sensor to measure the current of the output branch of the voltage-sharing capacitor 11. For example: connect the optical current sensor to the output branch of the voltage-sharing capacitor 11, so as to measure the current of the output branch of the voltage-sharing capacitor 11 by means of the optical principle, obtain an optical signal carrying the current parameter, and then the current of the output branch of the voltage-sharing capacitor 11, that is, the current parameter of the voltage-sharing capacitor 11, can be obtained by analyzing the optical signal.

[0074] Exemplarily, the voltage measurement module and the current measurement module can be communicatively connected to the monitoring system platform 13 respectively. The voltage measurement module can send the voltage parameters of the voltage-sharing capacitor 11 to the monitoring system platform 13 through a network, and the current measurement module can send the current parameters of the voltage-sharing capacitor 11 to the monitoring system platform 13 through a network, so that the monitoring system platform 13 can perform real-time online analysis based on the voltage parameters and current parameters of the voltage-sharing capacitor 11, thereby determining the current state of the voltage-sharing capacitor 11, and performing an online status warning based on the current state of the voltage-sharing capacitor 11. Among them, the current state of the voltage-sharing capacitor 11 can be used to represent the current working state of the voltage-sharing capacitor 11, or to represent the current performance state of the voltage-sharing capacitor 11, such as a healthy state, a damaged state, a decay state, a completely damaged state, etc.

[0075] For the monitoring system platform 13, it can adopt electrical physical principles to analyze the voltage parameters and current parameters of the voltage-sharing capacitor 11 to determine the current state of the voltage-sharing capacitor 11. For example: the capacitance value of the voltage-sharing capacitor can be calculated based on the voltage and current, and the current state of the voltage-sharing capacitor can be judged based on the capacitance value. Exemplarily, different capacitance thresholds can be set to obtain different capacitance value ranges, and different capacitance value ranges can correspond to different states of the voltage-sharing capacitor. Exemplarily, a state detection model or a prediction model can also be adopted to determine the current state of the voltage-sharing capacitor through in-depth analysis of the voltage parameters and current parameters; the state detection model or the prediction model can be a deep learning model, such as a neural network model, etc. The type of the deep learning model is not specifically limited in the embodiments of the present application.

[0076] Exemplarily, when the monitoring system platform 13 obtains the current state of the voltage-sharing capacitor 13 by analyzing the voltage parameters and current parameters of the voltage-sharing capacitor 11, it can also judge whether the current state of the voltage-sharing capacitor 13 is an abnormal state. If it is an abnormal state, a warning prompt message corresponding to the abnormal state can be output; Exemplarily, the abnormal state can be divided into multiple abnormal states according to types, such as a damaged state, a decay state, a completely damaged state, etc.; or, it can also be divided into multiple abnormal states according to the decay level, such as a first-level abnormal state, a second-level abnormal state, etc. The higher the state level (the smaller the level number), the weaker the performance of the voltage-sharing capacitor. For example, the performance of the voltage-sharing capacitor in the first-level abnormal state is worse than that in the second-level abnormal state.

[0077] The state monitoring system proposed in this embodiment includes a grading capacitor, an electrical parameter measurement circuit, and a monitoring system platform. The electrical parameter measurement circuit is respectively connected to the grading capacitor and the monitoring system platform. Among them, the electrical parameter measurement circuit is used to measure the electrical parameters of the grading capacitor and send the electrical parameters to the monitoring system platform. The electrical parameters include voltage parameters and current parameters, and the current parameters are measured by an optical current sensor. The monitoring system platform is used to analyze the electrical parameters, determine the current state of the grading capacitor, and output a warning prompt message when the current state is an abnormal state. That is, the embodiment of the present application proposes a state monitoring system capable of real-time online monitoring of the state of the grading capacitor. In this system, an electrical parameter measurement circuit for real-time online measurement of the electrical parameters of the grading capacitor is set, and a corresponding monitoring system platform is set. Thus, when the grading capacitor is in a working state, the current electrical parameters of the grading capacitor can be measured, and the current state of the grading capacitor can be analyzed and determined based on the current electrical parameters. The current state of the grading capacitor can reflect the actual performance of the grading capacitor. Therefore, when it is determined that the grading capacitor is abnormal, a warning prompt message can be output in time to achieve online monitoring and warning. It can not only improve the real-time performance of the grading capacitor performance detection, but also improve the detection efficiency of the grading capacitor performance detection, and improve the abnormal warning rate of the grading capacitor.

[0078] In an exemplary embodiment, an optional circuit structure of the electrical parameter measurement circuit is provided, as Figure 2 shown. The electrical parameter measurement circuit 12 includes a voltage measurement module 121, a current measurement module 122, and a comprehensive processing module 123. The input end of the voltage measurement module 121 is connected to both ends of the grading capacitor 11, and the output end of the voltage measurement module 121 is connected to the comprehensive processing module 123 through a wire. The input end of the current measurement module 122 is connected to the output branch of the grading capacitor 11, and the output end of the current measurement module 122 is connected to the comprehensive processing module 123 through a first optical fiber. Among them, the voltage measurement module 121 is used to measure the voltage parameters of the grading capacitor and transmit the voltage electrical signal carrying the voltage parameters to the comprehensive processing module 123 through a wire. The current measurement module 122 is used to measure the current parameters of the grading capacitor and transmit the current optical signal carrying the current parameters to the comprehensive processing module 123 through the first optical fiber. The current measurement module 121 includes an optical current sensor. The comprehensive processing module 123 is used to obtain the voltage parameters from the voltage electrical signal and the current parameters from the current optical signal, and send the voltage parameters and the current parameters to the monitoring system platform 13.

[0079] Exemplarily, the voltage measurement module 121 is connected across the equalizing capacitor 11 and can measure the voltage parameters of the equalizing capacitor 11. Then, the voltage electrical signal carrying the voltage parameters can be transmitted to the comprehensive processing module 123 through a wire. After receiving the voltage electrical signal, the comprehensive processing module 123 can analyze and determine the voltage parameters. Optionally, a voltage receiving unit for receiving the voltage electrical signal can be provided in the comprehensive processing module 123.

[0080] Exemplarily, the current measurement module 122 is connected to the output branch of the equalizing capacitor 11 and can measure the current parameters of the equalizing capacitor 11. Then, the current optical signal carrying the current parameters can be transmitted to the comprehensive processing module 123 through the first optical fiber. After receiving the current optical signal, the comprehensive processing module 123 can analyze and determine the current parameters. Optionally, a current receiving unit for receiving the current optical signal can be provided in the comprehensive processing module 123.

[0081] Exemplarily, when the comprehensive processing module 123 analyzes the voltage parameters and current parameters, it can send the voltage parameters and current parameters to the monitoring system platform 13 through the network. Optionally, the comprehensive processing module 123 can send the voltage parameters and current parameters to the monitoring system platform 13 through the network according to a preset sampling period. For example, when the preset sampling period is 1 minute, the voltage parameters and current parameters within the most recent 1 minute can be sent to the monitoring system platform 13. Among them, there can be multiple voltage parameters within 1 minute, and there can also be multiple current parameters within 1 second. The voltage parameters and current parameters can form a data pair according to the time parameter, and this data pair can include the voltage parameters and current parameters at the same moment, such as the voltage value and current value at the same moment. Optionally, the comprehensive processing module 123 can also send the voltage parameters within 1 minute as a voltage data group to the monitoring system platform 13, and send the current parameters within 1 minute as a current data group to the monitoring system platform 13.

[0082] For the current measurement module 122, it can include an optical current sensor, that is, the current measurement module is composed of the optical current sensor, which is used to measure the branch current of the equalizing capacitor. Refer to Figure 3As shown, it shows a structural schematic diagram of an optical current sensor; exemplarily, the optical current sensor may include a light source, an optical signal conversion module, a second optical fiber, an optical signal splitting module and a signal processing module, and the second optical fiber is wound around the output branch of the voltage-equalizing capacitor; wherein, the initial optical signal emitted by the light source is converted into linearly polarized light after being processed by the polarization state conversion of the optical signal conversion module, and the linearly polarized light enters the second optical fiber, and under the action of the magnetic field generated by the current of the output branch, the polarization plane of the linearly polarized light rotates, and the rotated linearly polarized light forms a first linearly polarized light and a second linearly polarized light that are perpendicular to each other after passing through the optical signal splitting module, and the signal processing module analyzes and processes the first linearly polarized light and the second linearly polarized light to generate a current optical signal carrying current parameters.

[0083] Exemplarily, the optical signal conversion module can also be called a polarization state conversion module, which is used to convert the polarization state of the initial optical signal emitted by the light source to obtain linearly polarized light; exemplary, the optical signal conversion module can include a polarizer; the converted linearly polarized light enters the second optical fiber, and when the second optical fiber is tightly wound around the current conductor of the output branch of the voltage-equalizing capacitor, a magnetic field is generated due to the power supply of the conductor of the output branch. The second optical fiber in the magnetic field is affected by the magneto-optical effect, and the polarization plane of the linearly polarized light in the second optical fiber rotates; exemplary, the second optical fiber here can be a single-mode sensing fiber.

[0084] The rotation angle of the polarization plane is The magnetic field intensity H and the second optical fiber length L satisfy:

[0085] (1)

[0086] V is the Verdet constant.

[0087] According to Ampere's circuit law, the magnetic field strength around a long straight wire is , where I is the conductor current and R is the conductor radius. Substituting into the above formula (1) we get:

[0088] (2)

[0089] Correspondingly, the expression of current I is:

[0090] (3)

[0091] Among them, the wire radius R, the rotation angle And the second optical fiber length L are all measurable known quantities.

[0092] Next, the rotated linearly polarized light enters the optical signal splitting module for signal splitting, forming a first linearly polarized light and a second linearly polarized light that are perpendicular to each other. Optionally, the optical signal splitting module can be a polarizer, such as a polarization prism. After the light passes through the polarization prism, it can be divided into two perpendicular polarized light beams. After the linearly polarized light passes through the current wire of the voltage equalizing capacitor output branch, affected by the magnetic field of the current wire, the polarization plane rotates. The rotated linearly polarized light then carries the corresponding current information. At this time, the rotated linearly polarized light is divided into a first linearly polarized light and a second linearly polarized light by the polarization prism, and under the action of the optical detector, it can be transmitted to the signal processing module. When the signal processing module receives the first linearly polarized light and the second linearly polarized light, it can detect the rotation angle of the first linearly polarized light and the rotation angle of the second linearly polarized light, so as to obtain the first rotation angle corresponding to the first linearly polarized light and the second rotation angle corresponding to the second linearly polarized light. Then, according to the first rotation angle and the second rotation angle, the rotation angle difference can be determined, and substituting the rotation angle difference into the above formula (3), the wire current of the voltage equalizing capacitor output branch can be calculated, that is, the current parameter of the voltage equalizing capacitor is obtained. Finally, the signal processing module can output a current optical signal carrying the current parameter, and transmit the current optical signal carrying the current parameter to the comprehensive processing module 123 through the first optical fiber.

[0093] Reference Figure 4 As shown, it shows a structural schematic diagram of a comprehensive processing module. Exemplarily, the comprehensive processing module 123 can include an electro-optical converter, an optical fiber receiver, and a data processor. Among them, the electro-optical converter is respectively connected to the voltage measurement module and the data processor, and the optical fiber receiver is respectively connected to the optical current sensor and the data processor. The electro-optical converter is used to convert the voltage electrical signal to obtain a voltage optical signal and transmit the voltage optical signal to the data processor. The optical fiber receiver is used to receive the current optical signal and transmit the current optical signal to the data processor. The data processor is used to obtain the voltage parameter from the voltage optical signal and the current parameter from the current optical signal.

[0094] Exemplarily, when the voltage measurement module 121 measures the voltage electrical signal across the voltage equalizing capacitor 11, it can transmit the voltage electrical signal to the electro-optical converter in the comprehensive processing module 123 through a wire. The electro-optical converter converts the voltage electrical signal carrying the voltage parameter into a voltage optical signal carrying the voltage parameter, and transmits the voltage optical signal carrying the voltage parameter to the data memory through the third optical fiber, so that the data memory can obtain and store the voltage parameter after parsing the voltage optical signal.

[0095] Exemplarily, after the current measurement module 122 measures the current in the output branch of the voltage-sharing capacitor 11 through the optical current sensor, that is, obtains the current optical signal carrying the current parameter, it can transmit the current optical signal carrying the current parameter to the comprehensive processing module 123 through the first optical fiber, and receive it through the optical fiber receiver in the comprehensive processing module 123. The optical fiber receiver then transmits the received current optical signal carrying the current parameter to the data memory through the fourth optical fiber, so that the data memory can obtain and store the current parameter after analyzing the current optical signal.

[0096] Further, the data memory in the comprehensive processing module 123 can send the stored voltage parameter and current parameter to the monitoring system platform 13 through the network. For example, it can report the voltage parameter and current parameter of the voltage-sharing capacitor 11 to the monitoring system platform 13 according to a preset sampling period.

[0097] Exemplarily, the monitoring system platform 13 can also send a parameter acquisition request to the comprehensive processing module 123. When the comprehensive processing module 123 receives the parameter acquisition request, it extracts the electrical parameters of the voltage-sharing capacitor from the data memory and feeds them back to the monitoring system platform. For example, the monitoring system platform 13 can obtain the voltage parameter and / or current parameter within a certain period of time. The comprehensive processing module 123 extracts the corresponding electrical parameters from the data memory according to the parameter identifier and time identifier carried in the parameter acquisition request. Among them, the parameter identifier is used to represent the voltage parameter and / or current parameter, and the time identifier is used to represent the requested time period.

[0098] In this embodiment, the electrical parameter measurement circuit may include a voltage measurement module, a current measurement module, and a comprehensive processing module. The voltage measurement module is used to detect the voltage across the voltage-sharing capacitor, the current measurement module is used to detect the branch current of the voltage-sharing capacitor, and the comprehensive processing module is used to process the voltage electrical signal and the current optical signal to obtain the voltage parameter and the current parameter. Among them, for current measurement, the branch current of the voltage-sharing capacitor is measured based on the Faraday effect. Through algorithm and fine calculation and analysis of the power circuit, the current value can be accurately restored, realizing high-precision and non-contact measurement. By adopting the detection principle in this example, the detection accuracy can be improved. In addition, the circuit structure provided in this example can improve the feasibility and implementability of online real-time monitoring of the performance of the voltage-sharing capacitor.

[0099] In an exemplary embodiment, referring to Figure 5 as shown, the above state monitoring system 10 may further include a laser power supply circuit 14, and the laser power supply circuit 14 is connected to the electrical parameter measurement circuit 12; the laser power supply circuit 14 is used to supply electrical energy to the electrical parameter measurement circuit 12.

[0100] In this embodiment, a laser is used as a stable and reliable energy source to supply power to the electrical parameter measurement circuit 12. Exemplarily, when the electrical parameter measurement circuit 12 includes a voltage measurement module 121, a current measurement module 122, and an integrated processing module 123, a laser is used as a stable and reliable energy source to supply power to the integrated processing circuit 123.

[0101] In an alternative implementation, referring to Figure 6 As shown, it shows a schematic circuit diagram of a laser power supply circuit 14. Among them, the laser power supply circuit 14 may include a drive power supply, a laser emitter, a photoelectric converter, and a direct current (DC) voltage stabilization circuit. The transmission part is composed of an optical fiber (such as a fifth optical fiber) and an insulator. Laser power supply triggers the laser emitter through the drive power supply. The laser emitter emits laser light, and the laser signal is transmitted to the photoelectric converter through the fifth optical fiber. After the laser signal is converted into an electrical signal (i.e., an analog signal) by the photoelectric converter, it is transmitted to the DC voltage stabilization circuit, that is, the photoelectric converter converts light energy into electrical energy, and then provides electrical energy to the integrated processing circuit after voltage stabilization by the DC voltage stabilization circuit.

[0102] In this embodiment, the method of using laser power supply to supply power to the electrical parameter measurement circuit can improve the stability and reliability of power supply, thereby further improving the stability of on-line performance monitoring of the equalizing capacitor.

[0103] In an exemplary embodiment, referring to Figure 7 As shown, the above monitoring system platform 13 may include an edge computing module 131, a depth analysis module 132, and a warning module 133; among them, the edge computing module 131 is used to perform difference analysis on the voltage parameter and the current parameter respectively according to the standard parameter library, and determine whether the equalizing capacitor is in an abnormal state according to the difference analysis result; the depth analysis module 132 is used to input the voltage parameter and the current parameter into a preset depth analysis model when the equalizing capacitor is in an abnormal state to determine the type of the abnormal state; the warning module 133 is used to output a corresponding warning prompt message according to the type of the abnormal state.

[0104] In an alternative implementation, the edge computing module 131 can be communicatively connected to the in-depth analysis module 132, and the in-depth analysis module 132 is communicatively connected to the early warning module 133. In this case, the edge computing module 131 can first perform differential analysis on the voltage parameter and the current parameter respectively according to the standard parameter library, and determine whether the voltage-sharing capacitor is in an abnormal state according to the differential analysis result. When it is determined that the voltage-sharing capacitor is in an abnormal state, a deep analysis request is sent to the in-depth analysis module 132. At this time, the in-depth analysis module 132 can input the voltage parameter and the current parameter into a preset in-depth analysis model to determine the type of the abnormal state, that is, to determine the specific abnormal state type of the voltage-sharing capacitor. Then, the in-depth analysis module 132 can send the specific abnormal state type of the voltage-sharing capacitor to the early warning module 133 so that the early warning module 133 can output a corresponding early warning prompt message according to the specific abnormal state type of the voltage-sharing capacitor.

[0105] Optionally, when the voltage-sharing capacitor is in an abnormal state, the types of its abnormal states can include but are not limited to a lossy state, an attenuation state, a damaged state, etc. The corresponding early warning prompt messages and early warning methods for different abnormal states can be different. When the degree of abnormality of the voltage-sharing capacitor is relatively high, the level of the corresponding early warning prompt is higher and the number of early warning methods is more, such as alarm devices, handheld terminal reminders, platform interface warnings, etc.

[0106] In another alternative implementation, the edge computing module 131 can also be communicatively connected to the early warning module 133, and the in-depth analysis module 132 is communicatively connected to the early warning module 133. In this case, the edge computing module 131 and the in-depth analysis module 132 can be two parallel analysis modules that simultaneously perform an abnormal state analysis on the voltage-sharing capacitor. Among them, the edge computing module 131 can determine whether the voltage-sharing capacitor is in an abnormal state, and the in-depth analysis module 132 can determine the specific abnormal state type of the voltage-sharing capacitor. Exemplarily, the output states of the two analysis modules can also be compared to further judge the analysis accuracy of the monitoring system platform for the current state of the voltage-sharing capacitor. For example: when the edge computing module 131 determines that the current state of the voltage-sharing capacitor is a normal state and the current state of the voltage-sharing capacitor output by the in-depth analysis module 132 is also a normal state, it is determined that the current state of the voltage-sharing capacitor is a normal state. On the contrary, if one party detects that the current state of the voltage-sharing capacitor is a normal state while the other party detects that the current state of the voltage-sharing capacitor is an abnormal state, for this situation, the output results of both parties can be sent to the platform user for manual verification; or, the state type output by the in-depth analysis module 132 can also be used as the current state of the voltage-sharing capacitor.

[0107] For the above-mentioned edge computing module 131, the specific implementation process of its judgment and analysis may include: First, the standard parameter library may include at least one standard voltage waveform and at least one standard current waveform, that is, the standard parameter library may be a standard waveform library. After the edge computing module 131 obtains the voltage parameter and current parameter of the voltage-sharing capacitor, it may first determine the actual voltage waveform according to the voltage parameter and determine the actual current waveform according to the current parameter. Then, perform difference analysis on the actual voltage waveform and each standard voltage waveform respectively to obtain at least one voltage difference; and perform difference analysis on the actual current waveform and each standard current waveform respectively to obtain at least one current difference. After that, compare each voltage difference with the preset voltage difference threshold, and compare each current difference with the preset current difference threshold. If there is at least one voltage difference greater than the preset voltage difference threshold, or there is at least one current difference greater than the preset current difference threshold, it is determined that the voltage-sharing capacitor is in an abnormal state.

[0108] Setting the edge computing module 131 in the monitoring system platform 13 can reduce the computing pressure of the platform and improve real-time performance. Exemplarily, before comparing with the standard waveform library, the edge computing module 131 can also first filter the acquired data, that is, remove the outliers in the data, such as filtering the outliers of the voltage parameter and filtering the outliers of the current parameter. Then, determine the actual voltage waveform according to the filtered voltage parameter and determine the actual current waveform according to the filtered current parameter.

[0109] Data filtering, as the first task of edge computing, aims to screen and remove the abnormal voltage values in the voltage parameter and the abnormal current values in the current parameter to obtain the effective voltage parameter and the effective current parameter, so as to ensure the accuracy of state monitoring. Exemplarily, when the monitoring system platform 13 receives the voltage parameter and current parameter sent by the electrical parameter measurement circuit 12 in the form of electromagnetic waves, the monitoring system platform 13 can obtain the voltage parameter signal and the current parameter signal. In this case, low-pass, high-pass or band-pass filtering algorithms can be used to denoise the voltage parameter signal and the current parameter signal. For example: for the collected voltage parameter signal and current parameter signal, if there is high-frequency noise interference, unnecessary high-frequency components can be removed through low-pass filtering to restore a relatively smooth fundamental wave signal to accurately obtain the effective voltage value and the effective current value for real-time volt-ampere monitoring of the voltage-sharing capacitor.

[0110] Then, the effective voltage waveform can be obtained according to the effective voltage parameter, and the effective current waveform can be obtained according to the effective current parameter. When comparing with the standard waveform library, the purpose is to compare and analyze the filtered effective voltage waveform and effective current waveform with each standard voltage waveform and each standard current waveform in the standard waveform library to determine the difference in waveform changes.

[0111] Finally, when judging the state according to the differences, the voltage difference and the current difference are analyzed by preset voltage difference thresholds and current difference thresholds, so as to quickly identify potential abnormal situations; it should be noted that the preset voltage difference thresholds and the preset current difference thresholds are determined based on historical data and are used to distinguish normal states from abnormal states. The preset voltage difference thresholds and the preset current difference thresholds can be fixed or dynamically changed based on historical data.

[0112] For the above-mentioned in-depth analysis module 132, the specific implementation process of its judgment and analysis may include: first, determining the actual voltage waveform according to the voltage parameters and the actual current waveform according to the current parameters; then, inputting the actual voltage waveform and the actual current waveform into a preset in-depth analysis model to determine the type of abnormal state. Exemplarily, the type of abnormal state may include, but is not limited to, different levels of abnormal states, or different types of abnormal states, such as damaged abnormality, attenuation abnormality, damage abnormality, etc.

[0113] Exemplarily, the above-mentioned inputting the actual voltage waveform and the actual current waveform into a preset in-depth analysis model to determine the type of abnormal state may further include: denoising the actual voltage waveform and the actual current waveform to obtain a denoised voltage waveform and a denoised current waveform; normalizing the denoised voltage waveform according to the preset voltage characteristics of the denoised voltage waveform to obtain a normalized voltage waveform; normalizing the denoised current waveform according to the preset current characteristics of the denoised current waveform to obtain a normalized current waveform; and inputting the normalized voltage waveform and the normalized current waveform into a preset in-depth analysis model to determine the type of abnormal state.

[0114] That is to say, before performing in-depth analysis processing, the actual voltage waveform and actual current waveform of the voltage-sharing capacitor can be denoised and normalized first. Then, the denoised and normalized voltage waveform and current waveform are input into a preset in-depth analysis model for state analysis, so as to output the current state of the voltage-sharing capacitor. Exemplarily, when performing denoising processing, wavelet transform can be used to remove the noise of the actual voltage waveform and actual current waveform, or other denoising methods can be used for denoising, such as mean filtering, median filtering, Gaussian filtering, low-pass filtering / high-pass filtering, etc. The embodiments of the present application do not make specific limitations in this regard. Exemplarily, when performing normalization processing, the waveform features can be extracted first, and then the waveform can be normalized according to the waveform features. The waveform features can include, but are not limited to, feature information such as wave peaks and wave valleys. For example, for the actual voltage waveform, the wave peak and wave valley features of the actual voltage waveform can be obtained first. Then, according to the wave peak and wave valley features, the actual voltage waveform is normalized to a specific voltage range to obtain a normalized voltage waveform. Similarly, the normalization processing operation of the actual current waveform is the same as that of the actual voltage waveform, and this example will not be repeated here.

[0115] Exemplarily, for the preset in-depth analysis model, it can also be trained before application to obtain a trained preset in-depth analysis model. When performing model training, the neural network can be trained according to different voltage parameters, different current parameters, and the corresponding state types of the voltage-sharing capacitor to obtain a preset in-depth analysis model. Among them, the state types of the voltage-sharing capacitor can include normal state (or healthy state), lossy state, attenuation state, damaged state, etc.

[0116] Reference Figure 8As shown, it shows a schematic diagram of the process of model training. The state detection principle based on neural networks may include: first, collecting the state signals of electrical equipment, such as the sample voltage waveform obtained based on the sample voltage parameters of the grading capacitor and the sample current waveform obtained based on the sample current parameters of the grading capacitor in this example. Then, using wavelet transform to remove the noise of the state signals of the electrical equipment, that is, denoising the sample voltage waveform and the sample current waveform to obtain the denoised sample voltage waveform and the denoised sample current waveform; then, extracting the state characteristics of the state signals of the electrical equipment and performing normalization processing on them, that is, performing normalization processing on the denoised sample voltage waveform and the denoised sample current waveform respectively to obtain the normalized sample voltage waveform and the normalized sample current waveform; immediately afterwards, performing sample data segmentation on the normalized sample voltage waveform and the normalized sample current waveform, taking a part of the normalized sample voltage waveform and the normalized sample current waveform as training data, and taking the other part of the normalized sample voltage waveform and the normalized sample current waveform as test data; it should be noted that the training data and the test data may also include the standard states of the grading capacitors corresponding to the normalized sample voltage waveform and the normalized sample current waveform.

[0117] When performing model training, first, an initial neural network model needs to be constructed. Then, based on the training data, this initial neural network model is trained, that is, the model learning process. During the training process, the initial neural network model can be iteratively trained based on the training error obtained from the training data until the preset iteration stop condition is met, and a trained neural network model can be obtained.

[0118] For the trained neural network model, it is also necessary to use the test data to test this trained neural network model to verify the accuracy or correctness of the trained neural network model; exemplarily, the trained neural network model can also be further optimized and trained based on the test error corresponding to the test data, so as to obtain the final neural network model as the preset deep learning model in the application stage.

[0119] Exemplarily, for the above neural network model, it may include but is not limited to Radial Basis Function Network (RBF), Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), etc. In the embodiments of this application, the network structure of the type of neural network is not specifically limited.

[0120] In this embodiment, by setting an edge computing module, a deep analysis module, and an early warning module on the monitoring system platform, when performing online real-time monitoring, in order to reduce the computing pressure on the platform, it is possible to first determine whether the grading capacitor is in an abnormal state based on the edge computing module. When the grading capacitor is in a normal state, the deep analysis module may not be called first. When the grading capacitor is in an abnormal state, the deep analysis module can be called to further accurately locate the type of abnormal state of the grading capacitor, and then targeted early warning prompts can be made through the early warning module, which can reduce the workload of the monitoring system platform and thus improve the efficiency of the monitoring system platform.

[0121] In an exemplary embodiment, an online monitoring scheme for a grading capacitor connected in series with an RPU board in a converter valve is provided. In this example, two electrical parameters, namely the voltage across the grading capacitor and the branch current, are taken as examples. Refer to Figure 9 As shown, among them, the voltage measurement module is connected across the grading capacitor through ports, and is used to measure the voltage parameter of the grading capacitor, and transmits the voltage electrical signal (i.e., the analog signal of the voltage) carrying the voltage parameter to the electro-optical converter of the comprehensive processing module through a wire. After the electro-optical converter converts the voltage electrical signal carrying the voltage parameter into a voltage optical signal carrying the voltage parameter, it is transmitted to the data memory for storage; in addition, the current measurement module is an optical current sensor based on the Faraday effect and using optical fiber to sense and transmit signals, which converts the analog signal of the branch current of the grading capacitor into a current optical signal carrying the current parameter, and is connected to the fiber optic receiver of the comprehensive processing module through an optical fiber. The fiber optic receiver transmits the current optical signal carrying the current parameter to the data memory for storage; finally, the data memory extracts the voltage parameter from the voltage optical signal and the current parameter from the current optical signal, and uploads the voltage parameter and the current parameter to the monitoring system platform to form an actual voltage waveform and an actual current waveform on the monitoring system platform.

[0122] The monitoring system platform can perform a preliminary analysis on the actual voltage waveform and the actual current waveform through the edge computing module. If an abnormality is detected, then deep learning is performed through the RBF neural network model, and the data is analyzed and compared to obtain the actual abnormal state of the grading capacitor, and targeted early warning prompts are made through the early warning module to achieve accurate warning. Exemplarily, the monitoring system platform can also determine the actual capacitance value of the grading capacitor according to the actual voltage waveform and the actual current waveform, and output and display the actual capacitance value to the platform user.

[0123] In addition, the online monitoring scheme also includes a laser power supply circuit to provide electrical energy for the comprehensive processing module. Among them, the optical energy can be converted into electrical energy through an optoelectronic converter, and then through an energy extraction circuit, such as a DC voltage stabilizing circuit, the electrical energy is voltage-stabilized and then used to supply power to various electrical components and modules that need power supply in the comprehensive processing circuit.

[0124] The on-line monitoring system in this embodiment can not only significantly improve the early warning ability of the voltage-sharing capacitor's electrical attenuation, but also greatly enhance the reliability and interpretability of the early warning results, providing more powerful guarantee for the safe operation of the power system.

[0125] In an exemplary embodiment, a state monitoring method is also provided. This state monitoring method can be applied to the state monitoring system in any of the above embodiments. The method includes:

[0126] Measuring the electrical parameters of the voltage-sharing capacitor through an electrical parameter measurement circuit, and sending the electrical parameters to the monitoring system platform; the electrical parameters include voltage parameters and current parameters, and the current parameters are measured by an optical current sensor;

[0127] Analyzing the electrical parameters through the monitoring system platform to determine the current state of the voltage-sharing capacitor, and outputting a warning prompt message when the current state is an abnormal state.

[0128] The state monitoring method in this embodiment corresponds to the state monitoring system in the above embodiments, and its implementation process can refer to the relevant content descriptions of the state monitoring system in the above embodiments, which will not be repeated here.

[0129] In an exemplary embodiment, referring to Figure 10 as shown, a converter valve 20 is also provided, which includes a recovery period protection module 21, a voltage-sharing capacitor 22, and an electrical parameter measurement circuit 23. The voltage-sharing capacitor 22 is connected in series with the output end of the recovery period protection module 21, and the electrical parameter measurement circuit 23 is connected to the voltage-sharing capacitor 22; the electrical parameter measurement circuit 23 is used to measure the electrical parameters of the voltage-sharing capacitor 22 and send the electrical parameters to the monitoring system platform, and the electrical parameters are used to instruct the monitoring system platform to analyze the electrical parameters, determine the current state of the voltage-sharing capacitor, and output a warning prompt message when the current state is an abnormal state.

[0130] That is to say, for the converter valve 20, an electrical parameter measurement circuit 23 for on-line state monitoring of the voltage-sharing capacitor 22 is arranged inside the converter valve 20. The electrical parameter measurement circuit 23 can collect the electrical parameters of the voltage-sharing capacitor 22 in real time online and communicate with the monitoring system platform through the network, so as to send the collected electrical parameters to the monitoring system platform for analysis and early warning in real time. Among them, the voltage-sharing capacitor 22 in the converter valve 20 can be a voltage-sharing capacitor connected in series with the recovery period protection module (i.e., the RPU board) 21.

[0131] In this embodiment, a converter valve capable of realizing online status monitoring is protected. The electrical parameter measurement circuit in the converter valve is used to collect the electrical parameters of the grading capacitors in the converter valve online, and the collected electrical parameters are sent to the monitoring system platform in the background for analysis and early warning. This can improve the real-time performance and accuracy of the grading capacitor performance monitoring, and also improve the detection efficiency of the grading capacitor performance monitoring. In addition, during the online monitoring process, no user participation is required, and the converter valve does not need to be disassembled or assembled, which can improve the operation convenience of the grading capacitor performance monitoring. Moreover, the monitoring system platform in the embodiment of the present application can comprehensively analyze the performance of the grading capacitors by means of a deep learning model, thereby improving the comprehensiveness of the grading capacitor performance detection, as well as the accuracy and precision of the grading capacitor performance detection.

[0132] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0133] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A condition monitoring system, characterized in that: The system comprises: a voltage-equalizing capacitor, an electrical parameter measurement circuit and a monitoring system platform, wherein the electrical parameter measurement circuit is connected to the voltage-equalizing capacitor and the monitoring system platform respectively; The electrical parameter measurement circuit is used to measure the electrical parameters of the voltage grading capacitor and send the electrical parameters to the monitoring system platform; the electrical parameters include voltage parameters and current parameters, and the current parameters are measured by an optical current sensor; The monitoring system platform is used to analyze the electrical parameters, determine the current state of the voltage-equalizing capacitor, and output warning information when the current state is abnormal.

2. The system according to claim 1, characterized in that The electrical parameter measurement circuit includes a voltage measurement module, a current measurement module and a comprehensive processing module, wherein the input end of the voltage measurement module is connected to the two ends of the voltage-equalizing capacitor, the output end of the voltage measurement module is connected to the comprehensive processing module through a wire, the input end of the current measurement module is connected to the output branch of the voltage-equalizing capacitor, and the output end of the current measurement module is connected to the comprehensive processing module through a first optical fiber; The voltage measurement module is used to measure the voltage parameter of the voltage balancing capacitor and transmit the voltage electrical signal carrying the voltage parameter to the comprehensive processing module through the wire; The current measurement module is used to measure the current parameter of the voltage-equalizing capacitor and transmit the current optical signal carrying the current parameter to the integrated processing module through the first optical fiber; the current measurement module includes the optical current sensor; The comprehensive processing module is used to obtain the voltage parameter from the voltage electrical signal and the current parameter from the current optical signal, and send the voltage parameter and the current parameter to the monitoring system platform.

3. The system according to claim 2, characterized in that The optical current sensor comprises a light source, an optical signal conversion module, a second optical fiber, an optical signal splitting module and a signal processing module, wherein the second optical fiber is wound around the output branch of the voltage balancing capacitor; The initial light signal emitted by the light source is converted into linearly polarized light after polarization state conversion processing by the optical signal conversion module. The linearly polarized light enters the second optical fiber. Under the action of the magnetic field generated by the current in the output branch, the polarization plane of the linearly polarized light rotates. The rotated linearly polarized light passes through the optical signal splitting module to form a first linearly polarized light and a second linearly polarized light that are perpendicular to each other. The signal processing module analyzes and processes the first linearly polarized light and the second linearly polarized light to generate a current optical signal carrying the current parameters.

4. The system according to claim 2, characterized in that The integrated processing module includes an electro-optical converter, an optical fiber receiver and a data processor, wherein the electro-optical converter is connected to the voltage measurement module and the data processor respectively, and the optical fiber receiver is connected to the optical current sensor and the data processor respectively; The electro-optical converter is used to convert the voltage electrical signal to obtain a voltage optical signal, and transmit the voltage optical signal to the data processor; The optical fiber receiver is used to receive the current optical signal and transmit the current optical signal to the data processor; The data processor is used to obtain the voltage parameter from the voltage optical signal, and to obtain the current parameter from the current optical signal.

5. The system according to any one of claims 1 to 4, characterized in that: The system further comprises: a laser energy supply circuit, the laser energy supply circuit being connected to the electrical parameter measurement circuit; The laser power supply circuit is used to provide electrical energy to the electrical parameter measurement circuit.

6. The system according to any one of claims 1 to 4, characterized in that: The monitoring system platform includes an edge computing module, a deep analysis module and an early warning module; The edge computing module is used to perform difference analysis on the voltage parameter and the current parameter respectively according to the standard parameter library, and determine whether the voltage grading capacitor is in an abnormal state according to the difference analysis result; The depth analysis module is used to input the voltage parameter and the current parameter into a preset depth analysis model to determine the type of the abnormal state when the voltage grading capacitor is in an abnormal state; The early warning module is used to output corresponding early warning prompt information according to the type of the abnormal state.

7. The system according to claim 6, characterized in that The standard parameter library includes at least one standard voltage waveform and at least one standard current waveform. The voltage parameter and the current parameter are respectively subjected to difference analysis according to the standard parameter library, and whether the voltage grading capacitor is in an abnormal state is determined according to the difference analysis result, including: determining an actual voltage waveform according to the voltage parameter, and determining an actual current waveform according to the current parameter; Performing difference analysis on the actual voltage waveform and at least one of the standard voltage waveforms to obtain at least one voltage difference; Performing difference analysis on the actual current waveform and at least one of the standard current waveforms to obtain at least one current difference; If at least one of the voltage differences is greater than a preset voltage difference threshold, or at least one of the current differences is greater than a preset current difference threshold, it is determined that the voltage grading capacitor is in an abnormal state.

8. The system according to claim 6, characterized in that The step of inputting the voltage parameter and the current parameter into a preset depth analysis model to determine the type of the abnormal state includes: determining an actual voltage waveform according to the voltage parameter, and determining an actual current waveform according to the current parameter; The actual voltage waveform and the actual current waveform are input into a preset depth analysis model to determine the type of the abnormal state.

9. The system according to claim 8, characterized in that The inputting the actual voltage waveform and the actual current waveform into a preset depth analysis model to determine the type of the abnormal state includes: De-noising the actual voltage waveform and the actual current waveform to obtain a de-noised voltage waveform and a de-noised current waveform; According to a preset voltage feature of the denoised voltage waveform, the denoised voltage waveform is normalized to obtain a normalized voltage waveform; According to the preset current characteristics of the de-noised current waveform, the de-noised current waveform is normalized to obtain a normalized current waveform; The normalized voltage waveform and the normalized current waveform are input into a preset depth analysis model to determine the type of the abnormal state.

10. A flow control valve, characterized in that: It includes a recovery period protection module, a voltage balancing capacitor and an electrical parameter measurement circuit, wherein the voltage balancing capacitor is connected in series with the output end of the recovery period protection module, and the electrical parameter measurement circuit is connected with the voltage balancing capacitor; The electrical parameter measurement circuit is used to measure the electrical parameters of the equalizing capacitor and send the electrical parameters to the monitoring system platform. The electrical parameters are used to instruct the monitoring system platform to analyze the electrical parameters, determine the current state of the equalizing capacitor, and output early warning information when the current state is abnormal.

Images