Reactor turn-to-turn short circuit fault identification method based on Lissajous figure and support vector regression

Abstract

The invention relates to an electric reactor turn-to-turn short circuit fault identification method and device based on a Lissajous figure and support vector regression, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a reactor reconstruction signal set; based on the reactor reconstruction signal set, generating a Lissajous figure corresponding to each reactor; for any reactor, determining the inclination angle of the Lissajous figure corresponding to the reactor, and determining the fault degree of the reactor based on the inclination angle; fitting the inclination angle and the fault degree corresponding to each reactor by adopting support vector regression to obtain a support vector regression fitting curve; determining an inclination angle when the fault degree is a preset degree in the support vector regression fitting curve, and taking the inclination angle when the fault degree is the preset degree as a fault threshold value; the fault threshold value is used for identifying whether the turn-to-turn short circuit fault occurs in any reactor or not in real time. By adopting the method, the initial turn-to-turn short circuit fault of the reactor can be detected timely and efficiently in real time.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method, device, system, storage medium and computer program product for identifying reactor turn-to-turn short-circuit faults based on Lissajous diagrams and support vector regression. Background Art

[0002] In the power system, the magnetically controlled controllable shunt reactor is a new type of dynamic reactive power compensation equipment. Because of its continuously adjustable reactive power capacity and simple and reliable control method, its application in the field of high-voltage AC power transmission has developed rapidly and has been applied in engineering projects in AC power grids of multiple voltage levels such as 220kV, 400kV, 500kV and 750kV.

[0003] Internal winding faults of magnetically controlled shunt reactors, especially turn-to-turn short circuits, are one of the main causes of fire accidents in magnetically controlled shunt reactors. At present, the main methods for detecting turn-to-turn short circuit faults of magnetically controlled shunt reactors include spatial magnetic field detection method, electrical parameter detection method, frequency response method, etc. In the early stage of a reactor fault, due to the slight change in the internal winding state, the existing turn-to-turn short circuit fault detection methods have poor sensitivity and are mainly based on offline detection. In addition, some detection methods will damage the reactor body and affect the normal operation of the reactor, and cannot detect the initial turn-to-turn short circuit condition of the reactor in a timely manner.

[0004] Therefore, the conventional technology has the problem of being unable to timely and efficiently detect the initial turn-to-turn short circuit condition of the reactor in real time. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for identifying reactor turn-to-turn short-circuit faults based on Lissajous diagrams and support vector regression, which can timely, efficiently and in real time detect the initial turn-to-turn short-circuit condition of the reactor in response to the above-mentioned technical problems.

[0006] A method for identifying inter-turn short-circuit faults of reactors based on Lissajous diagrams and support vector regression, the method comprising:

[0007] Acquire a reactor reconstruction signal set; the reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor; the voltage reconstruction signal and the current reconstruction signal corresponding to any reactor are obtained after signal reconstruction of the port voltage signal and the port current signal of the reactor;

[0008] Based on the reactor reconstruction signal set, a Lissajous figure corresponding to each reactor is generated; the Lissajous figure corresponding to any reactor represents the change trend of the voltage waveform and current waveform of the reactor;

[0009] For any reactor, determining the tilt angle of the Lissajous figure corresponding to the reactor, and determining the fault degree of the reactor based on the tilt angle;

[0010] Support vector regression is used to fit the tilt angle and fault degree corresponding to each reactor, and a support vector regression fitting curve is obtained;

[0011] The inclination angle when the fault degree is a preset degree is determined in the support vector regression fitting curve, and the inclination angle when the fault degree is a preset degree is used as the fault threshold; the fault threshold is used to identify in real time whether a turn-to-turn short circuit fault occurs in any reactor.

[0012] In an exemplary embodiment, obtaining a reactor reconstruction signal set includes:

[0013] Acquire a reactor voltage and current signal set; the reactor voltage and current signal set includes a port voltage signal and a port current signal of each reactor;

[0014] Extracting the power frequency components of the port voltage signal and the port current signal of any reactor to obtain the voltage reconstruction signal and the current reconstruction signal of any reactor;

[0015] A reactor reconstruction signal set is generated based on the voltage reconstruction signal and the current reconstruction signal of each reactor.

[0016] In an exemplary embodiment, obtaining a reactor voltage and current signal set includes:

[0017] Construct a finite element simulation model of the reactor and obtain simulation condition configuration information; the simulation condition configuration information is configured with simulation conditions for the reactor in a healthy state and simulation conditions in different fault states; different fault states correspond to different fault locations or different fault degrees;

[0018] Based on different simulation conditions configured by the simulation condition configuration information, the reactor finite element simulation model is simulated to obtain a reactor voltage and current simulation signal set;

[0019] The reactor voltage and current simulation signal set is used as the reactor voltage and current signal set.

[0020] In an exemplary embodiment, support vector regression is used to fit the tilt angle and fault degree corresponding to each reactor to obtain a support vector regression fitting curve, including:

[0021] The tilt angle corresponding to each reactor is taken as the dependent variable, the fault degree corresponding to each reactor is taken as the independent variable, and based on the dependent variable and the independent variable, the optimization target and constraint conditions for the support vector regression fitting curve are constructed;

[0022] Based on the tilt angle and fault degree corresponding to each reactor, the support vector regression method is used to solve the optimization target while satisfying the constraints, and the support vector regression fitting curve is obtained.

[0023] In an exemplary embodiment, after the step of taking the inclination angle when the fault degree is a preset degree as the fault threshold, the method further comprises:

[0024] Obtain the real-time voltage signal and real-time current signal corresponding to any reactor;

[0025] Based on the real-time voltage signal and the real-time current signal corresponding to any reactor, a real-time Lissajous figure of any reactor is generated;

[0026] When the inclination angle corresponding to the real-time Lissajous figure of any reactor is greater than the fault threshold, it is determined that a turn-to-turn short circuit fault occurs in any reactor.

[0027] In an exemplary embodiment, the method further comprises:

[0028] In the system interface of the reactor inter-turn short-circuit fault detection system, the real-time Lissajous figure of any reactor and the inclination angle corresponding to the real-time Lissajous figure of any reactor are displayed, as well as the support vector regression fitting curve.

[0029] A device for identifying inter-turn short-circuit faults of reactors based on Lissajous diagrams and support vector regression, the device comprising:

[0030] An acquisition module is used to acquire a reactor reconstruction signal set; the reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor; the voltage reconstruction signal and the current reconstruction signal corresponding to any reactor are obtained after signal reconstruction of the port voltage signal and the port current signal of the reactor;

[0031] A generation module is used to generate Lissajous figures corresponding to each reactor based on the reactor reconstruction signal set; the Lissajous figure corresponding to any reactor represents the change trend of the voltage waveform and current waveform of the reactor;

[0032] A determination module, for determining, for any reactor, an inclination angle of a Lissajous figure corresponding to the reactor, and determining a fault degree of the reactor based on the inclination angle;

[0033] A fitting module, used to fit the tilt angle and fault degree corresponding to each reactor by using support vector regression to obtain a support vector regression fitting curve;

[0034] The identification module is used to determine the inclination angle when the fault degree is a preset degree in the support vector regression fitting curve, and use the inclination angle when the fault degree is the preset degree as the fault threshold; the fault threshold is used to identify in real time whether any inductor has a turn-to-turn short circuit fault.

[0035] A reactor inter-turn short-circuit fault identification system based on Lissajous figures and support vector regression, the system includes a first interface for displaying real-time voltage waveforms and real-time current waveforms, a second interface for displaying real-time Lissajous figures and the inclination angles corresponding to the real-time Lissajous figures, and a third interface for processing reactor voltage and current signal sets.

[0036] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0037] A computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0038] The above-mentioned method, device, computer equipment, storage medium and computer program product for identifying short-circuit faults between turns of reactors based on Lissajous figures and support vector regression obtain a reactor reconstruction signal set; the reactor reconstruction signal set includes voltage reconstruction signals and current reconstruction signals corresponding to each reactor; the voltage reconstruction signal and current reconstruction signal corresponding to any reactor are obtained after signal reconstruction of the port voltage signal and the port current signal of the reactor; based on the reactor reconstruction signal set, a Lissajous figure corresponding to each reactor is generated; the Lissajous figure corresponding to any reactor represents the change trend of the voltage waveform and the current waveform of the reactor; for any reactor, the corresponding Lissajous figure of the reactor is determined The inclination angle of the Lissajous figure is determined, and based on the inclination angle, the fault degree of the reactor is determined; the inclination angle and fault degree corresponding to each reactor are fitted by support vector regression to obtain a support vector regression fitting curve; the inclination angle when the fault degree is a preset degree is determined in the support vector regression fitting curve, and the inclination angle when the fault degree is the preset degree is used as the fault threshold; the fault threshold is used to identify in real time whether any reactor has a turn-to-turn short-circuit fault; in this way, the problems of the turn-to-turn short-circuit fault detection method mainly relying on offline detection, cross sensitivity, and single detection feature quantity can be solved, and the initial turn-to-turn short-circuit condition of the reactor can be detected in time, thereby improving the accuracy and efficiency of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 1. It is an application environment diagram of a method for identifying a reactor turn-to-turn short-circuit fault based on Lissajous diagram and support vector regression in one embodiment;

[0041] Figure 2 A schematic diagram of a flow chart of a method for identifying a reactor turn-to-turn short-circuit fault based on Lissajous diagrams and support vector regression in one embodiment;

[0042] Figure 3 A schematic diagram of a support vector regression fitting curve in one embodiment;

[0043] Figure 4 A schematic flow chart of a method for obtaining a reactor reconstruction signal set in one embodiment;

[0044] Figure 5 A flowchart of a method for identifying a reactor turn-to-turn short-circuit fault based on Lissajous diagrams and support vector regression in one embodiment;

[0045] Figure 6 A schematic diagram of a system interface of a reactor inter-turn short-circuit fault detection system in one embodiment;

[0046] Figure 7 A schematic diagram of a flow chart of a method for identifying a reactor turn-to-turn short-circuit fault based on Lissajous diagrams and support vector regression in another embodiment;

[0047] Figure 8 A structural block diagram of a reactor inter-turn short-circuit fault identification device based on Lissajous diagram and support vector regression in one embodiment;

[0048] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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.

[0050] The method for identifying a short-circuit fault between turns of a reactor based on a Lissajous diagram and support vector regression provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 obtains a reactor reconstruction signal set; the reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor; the voltage reconstruction signal and the current reconstruction signal corresponding to any reactor are obtained after signal reconstruction of the port voltage signal and the port current signal of the reactor; the server 104 generates a Lissajous figure corresponding to each reactor based on the reactor reconstruction signal set; the Lissajous figure corresponding to any reactor represents the change trend of the voltage waveform and the current waveform of the reactor; the server 104 determines the inclination angle of the Lissajous figure corresponding to any reactor, and determines the fault degree of the reactor based on the inclination angle; the server 104 uses support vector regression to fit the inclination angle and the fault degree corresponding to each reactor to obtain a support vector regression fitting curve; the server 104 determines the inclination angle when the fault degree is a preset degree in the support vector regression fitting curve, and uses the inclination angle when the fault degree is the preset degree as the fault threshold; the fault threshold is used to identify in real time whether any reactor has a turn-to-turn short circuit fault. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0051] In an exemplary embodiment, Figure 2 As shown in the figure, a method for identifying inter-turn short-circuit faults in reactors based on Lissajous diagrams and support vector regression is provided. Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 202 to 210. Among them:

[0052] Step 202: Acquire a reactor reconstruction signal set.

[0053] The reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor. The voltage reconstruction signal and the current reconstruction signal corresponding to any reactor are obtained by reconstructing the port voltage signal and the port current signal of the reactor.

[0054] Among them, the port voltage signal of the reactor can be expressed as , the port current signal can be expressed as , the signal reconstruction method can be expressed as:

[0055] ;

[0056] Among them, the frequency Take 50Hz, For extraction The amplitude of For extraction The amplitude of For extraction The phase of For extraction phase.

[0057] Optionally, the server obtains a reactor reconstruction signal set.

[0058] Step 204 , generating Lissajous figures corresponding to each reactor based on the reactor reconstruction signal set; the Lissajous figure corresponding to any reactor represents the variation trend of the voltage waveform and current waveform of the reactor.

[0059] Among them, the expression of Lissajous figure is:

[0060] ;

[0061] Optionally, the server generates a Lissajous figure corresponding to each reactor based on the reactor reconstruction signal set, that is, based on the voltage reconstruction signal and the current reconstruction signal corresponding to each reactor.

[0062] Step 206: for any reactor, determine the inclination angle of the Lissajous figure corresponding to the reactor, and determine the fault degree of the reactor based on the inclination angle.

[0063] Among them, the tilt angle is the characteristic parameter of the Lissajous figure and can be expressed as , tilt angle The calculation expression is:

[0064] ;

[0065] Among them, the fault degree of the reactor is determined based on the tilt angle corresponding to the Lissajous figure of the reactor. In actual applications, the tilt angle is calculated according to the Lissajous figure data of each reactor, and the fault degree of the reactor is determined according to the tilt angle of the Lissajous figure of each reactor, and a fault degree label is added to the Lissajous figure data of each reactor. By adding label classification, healthy reactors are marked as "healthy windings", and faulty reactors are marked as "mild faults", "moderate faults" or "severe faults", among which the fault degree of 2.5%~5% is "mild faults", 5%~10% is "moderate faults", and 10%~20% is "severe faults".

[0066] Optionally, for any reactor, the server determines the tilt angle of the Lissajous figure corresponding to the reactor, and then determines the fault degree of the reactor based on the tilt angle.

[0067] Step 208: Use support vector regression to fit the tilt angle and fault degree corresponding to each reactor to obtain a support vector regression fitting curve.

[0068] Among them, the support vector regression fitting curve is as follows Figure 3 As shown, Figure 3 The vertical axis unit is degree, which represents the size of the tilt angle, and the horizontal axis unit is %, which represents the degree of fault.

[0069] Optionally, the server uses support vector regression to fit the tilt angle and fault degree corresponding to each reactor to obtain a support vector regression fitting curve.

[0070] Step 210, determining the inclination angle when the fault degree is a preset degree in the support vector regression fitting curve, and taking the inclination angle when the fault degree is the preset degree as the fault threshold; the fault threshold is used to identify in real time whether any reactor has a turn-to-turn short circuit fault.

[0071] The preset degree may refer to a failure degree of 2.5%. Figure 3 It is shown that the tilt angle is 23.6% when the fault level is 2.5%.

[0072] Optionally, the inclination angle when the fault degree is 2.5% is determined in the support vector regression fitting curve as the fault threshold. The server can display the inclination angle when the fault degree is 2.5% and the corresponding Lissajous image on the system interface of the reactor inter-turn short-circuit fault detection system. Subsequently, it can be determined whether the reactor has a fault by comparing with the fault threshold.

[0073] In the above-mentioned method for identifying short-circuit faults between turns of reactors based on Lissajous figures and support vector regression, a reactor reconstruction signal set is obtained; the reactor reconstruction signal set includes voltage reconstruction signals and current reconstruction signals corresponding to each reactor; the voltage reconstruction signal and current reconstruction signal corresponding to any reactor are obtained after signal reconstruction of the port voltage signal and the port current signal of the reactor; based on the reactor reconstruction signal set, a Lissajous figure corresponding to each reactor is generated; the Lissajous figure corresponding to any reactor represents the change trend of the voltage waveform and the current waveform of the reactor; for any reactor, the inclination angle of the Lissajous figure corresponding to the reactor is determined, Based on the tilt angle, the fault degree of the reactor is determined; support vector regression is used to fit the tilt angle and fault degree corresponding to each reactor to obtain a support vector regression fitting curve; the tilt angle when the fault degree is a preset degree is determined in the support vector regression fitting curve, and the tilt angle when the fault degree is the preset degree is used as the fault threshold; the fault threshold is used to identify in real time whether any reactor has a turn-to-turn short-circuit fault; in this way, the problems of the turn-to-turn short-circuit fault detection method mainly relying on offline detection, cross sensitivity, and single detection feature quantity can be solved, and the initial turn-to-turn short-circuit condition of the reactor can be detected in time, thereby improving the accuracy and efficiency of fault diagnosis.

[0074] In an exemplary embodiment, Figure 4 As shown, step 202 includes steps 402 to 406. Among them:

[0075] Step 402: Acquire a set of reactor voltage and current signals.

[0076] The reactor voltage and current signal set includes a port voltage signal and a port current signal of each reactor.

[0077] Optionally, the server obtains a set of reactor voltage and current signals.

[0078] Step 404 , extracting the power frequency components of the port voltage signal and the port current signal of any reactor to obtain the voltage reconstruction signal and the current reconstruction signal of any reactor.

[0079] Optionally, for any reactor, the server extracts the power frequency components of the port voltage signal and the port current signal of the reactor to obtain the voltage reconstruction signal and the current reconstruction signal of the reactor.

[0080] Step 406: Generate a reactor reconstruction signal set based on the voltage reconstruction signal and the current reconstruction signal of each reactor.

[0081] Optionally, the server generates a reactor reconstruction signal set based on the voltage reconstruction signal and the current reconstruction signal of each reactor.

[0082] In this embodiment, a reactor voltage and current signal set is obtained; the reactor voltage and current signal set includes the port voltage signal and the port current signal of each reactor; the power frequency component of the port voltage signal and the port current signal of any reactor is extracted to obtain the voltage reconstruction signal and the current reconstruction signal of any reactor; based on the voltage reconstruction signal and the current reconstruction signal of each reactor, a reactor reconstruction signal set is generated; in this way, the reactor voltage and current signal set can be reconstructed to restore the frequency, amplitude, phase and other information of the original signal as much as possible, which is conducive to the subsequent generation of more accurate Lissajous figures.

[0083] In an exemplary embodiment, obtaining a reactor voltage and current signal set includes: constructing a reactor finite element simulation model and obtaining simulation condition configuration information; the simulation condition configuration information is configured with simulation conditions for the reactor in a healthy state and simulation conditions under different fault states; different fault states correspond to different fault locations or different fault degrees; based on the different simulation conditions configured by the simulation condition configuration information, simulating the reactor finite element simulation model to obtain a reactor voltage and current simulation signal set; and using the reactor voltage and current simulation signal set as the reactor voltage and current signal set.

[0084] The reactor finite element simulation model may be a finite element simulation model built for an actual reactor.

[0085] The simulation condition configuration information is configured with simulation conditions for the reactor in a healthy state and simulation conditions in different fault states, and different fault states correspond to different fault locations and different fault degrees.

[0086] For the magnetically controlled controllable shunt reactor, there are 20 layers of coils from the inside to the outside, and each layer of coils can correspond to a fault location. The fault degree can include a slight fault, a moderate fault, and a severe fault. The purpose of setting different fault locations and different fault degrees is to obtain the voltage and current simulation signals of the reactor under different fault conditions, so as to better predict the fault location and judge the fault condition of the magnetically controlled controllable shunt reactor.

[0087] Optionally, the server constructs a finite element simulation model of the reactor based on the actual reactor and obtains simulation condition configuration information. The server simulates the finite element simulation model of the reactor based on different simulation conditions configured by the simulation condition configuration information, obtains a large number of reactor voltage and current simulation signals, and generates a reactor voltage and current signal set.

[0088] In practical applications, a large number of reactor voltage and current simulation signals obtained through simulation can be used as a reactor voltage and current signal set. The actual data of operating reactors measured by mutual inductors, the collected historical data of reactors, and online public data such as papers and public databases can be used as a reactor voltage and current signal set. The above various types of data can be generated into a set of reactor voltage and current signal sets.

[0089] In the present embodiment, a finite element simulation model of a reactor is constructed, and simulation condition configuration information is obtained; the simulation condition configuration information is configured with simulation conditions for the reactor in a healthy state and simulation conditions under different fault states; different fault states correspond to different fault locations or different fault degrees; based on the different simulation conditions configured by the simulation condition configuration information, the finite element simulation model of the reactor is simulated to obtain a reactor voltage and current simulation signal set; the reactor voltage and current simulation signal set is used as the reactor voltage and current signal set; in this way, a large number of reactor voltage and current signal sets can be quickly obtained through finite element simulation, which is conducive to the subsequent fitting of a more accurate support vector regression fitting curve.

[0090] In an exemplary embodiment, support vector regression is used to fit the tilt angle and fault degree corresponding to each reactor to obtain a support vector regression fitting curve, including: taking the tilt angle corresponding to each reactor as the dependent variable, taking the fault degree corresponding to each reactor as the independent variable, and constructing the optimization target and constraint conditions for the support vector regression fitting curve based on the dependent variable and the independent variable; based on the tilt angle and fault degree corresponding to each reactor, support vector regression is used to solve the optimization target while satisfying the constraint conditions to obtain the support vector regression fitting curve.

[0091] Among them, support vector regression is used for fitting, that is, a function is found , where w is the weight vector and b is the bias, so that all predicted values and the true value The error between within, that is At the same time, in order to control the complexity of the model, support vector regression introduces a regularization term .

[0092] Among them, the optimization objective can be expressed as:

[0093] ;

[0094] in, is a regularization term that controls the complexity of the model; is a penalty parameter that controls the tolerance to errors; and is the slack variable, representing the excess error.

[0095] The constraints can be expressed as:

[0096] .

[0097] The constraints ensure that the prediction error of most data points is within the range, while allowing some data points to exceed the range but will be punished. Support vector regression can process nonlinear data through kernel functions (such as linear kernel, RBF kernel, polynomial kernel, etc.). The role of the kernel function is to map the data to a high-dimensional space so that it can be linearly separable in the high-dimensional space, thereby realizing nonlinear regression.

[0098] Optionally, the server takes the tilt angle corresponding to each reactor as the dependent variable, i.e., the y-axis, and the fault degree corresponding to each reactor as the independent variable, i.e., the x-axis. The server determines the optimization objective and constraints of the support vector regression fitting curve. Based on the tilt angle and fault degree corresponding to each reactor, the server uses the support vector regression method to solve the optimization objective while satisfying the constraints, and obtains the support vector regression fitting curve.

[0099] In this embodiment, the tilt angle corresponding to each reactor is taken as the dependent variable, the fault degree corresponding to each reactor is taken as the independent variable, and based on the dependent variable and the independent variable, the optimization target and constraint conditions for the support vector regression fitting curve are constructed; based on the tilt angle and the fault degree corresponding to each reactor, the support vector regression method is used to solve the optimization target while satisfying the constraint conditions, and the support vector regression fitting curve is obtained; in this way, the support vector regression can be used to diagnose the openness of the reactor, effectively avoiding misjudgment caused by human judgment, and improving the accuracy of the reactor's inter-turn short-circuit fault detection.

[0100] In an exemplary embodiment, after the step of taking the inclination angle when the fault degree is a preset degree as a fault threshold, the method also includes: obtaining a real-time voltage signal and a real-time current signal corresponding to any reactor; generating a real-time Lissajous figure of any reactor based on the real-time voltage signal and the real-time current signal corresponding to any reactor; when the inclination angle corresponding to the real-time Lissajous figure of any reactor is greater than the fault threshold, determining that a turn-to-turn short circuit fault occurs in any reactor.

[0101] The real-time voltage signal may be a voltage signal of any reactor acquired in real time by a voltage transformer.

[0102] The real-time current signal may be a current signal of any reactor collected in real time by a current transformer.

[0103] The real-time Lissajous figure may be a Lissajous figure generated by the real-time voltage signal and the real-time current signal of any reactor.

[0104] Optionally, the server obtains the real-time voltage signal and the real-time current signal corresponding to any reactor, and generates a real-time Lissajous figure of the reactor based on the real-time voltage signal and the real-time current signal corresponding to the reactor. When the inclination angle corresponding to the real-time Lissajous figure of the reactor is greater than the fault threshold (the inclination angle when the fault degree is 2.5%), the server determines that a turn-to-turn short circuit fault occurs in the reactor.

[0105] In practical applications, voltage transformers (PT) and current transformers (CT) can be used to synchronously collect the voltage / current signals of the reactor ports in a healthy state. and , and extract the power frequency component to reconstruct the voltage and current signals, and perform signal reconstruction. Use the reconstructed signal to draw the Lissajous figure, and calculate its characteristic parameter tilt angle After obtaining the characteristic parameters, take the inclination angle when the fault degree is 2.5% If the value is greater than the threshold, it indicates that the reactor is faulty.

[0106] In this embodiment, by acquiring the real-time voltage signal and the real-time current signal corresponding to any reactor; generating a real-time Lissajous figure of any reactor based on the real-time voltage signal and the real-time current signal corresponding to any reactor; when the inclination angle corresponding to the real-time Lissajous figure of any reactor is greater than the fault threshold, it is determined that any reactor has a turn-to-turn short-circuit fault, and whether the reactor has a fault can be detected in real time, which is conducive to timely identification of the turn-to-turn short-circuit fault of the reactor.

[0107] In order to facilitate the understanding of those skilled in the art, Figure 5 A flowchart of a method for identifying an inter-turn short-circuit fault of a reactor based on a Lissajous figure and support vector regression is also exemplified, and the steps in the flowchart include: collecting voltage signals and current signals of an MCSR (magnetically controlled shunt reactor) to draw a Lissajous figure; based on the Lissajous figure, extracting characteristic parameters and determining the degree of fault; based on the extracted fault parameters and the determined degree of fault, fitting a curve using support vector regression, and determining the inclination angle of the curve at a fault degree of 2.5% as the fault threshold, and subsequently judging the fault condition of the reactor based on the fault threshold.

[0108] In an exemplary embodiment, the method also includes: displaying the real-time Lissajous figure of any reactor and the inclination angle corresponding to the real-time Lissajous figure of any reactor in the system interface of the reactor inter-turn short-circuit fault detection system, and displaying the support vector regression fitting curve.

[0109] Optionally, the server displays the real-time Lissajous figure of any reactor and the inclination angle corresponding to the real-time Lissajous figure of any reactor in the system interface of the reactor inter-turn short-circuit fault detection system, and displays the support vector regression fitting curve.

[0110] Figure 6 The system interface of a reactor inter-turn short-circuit fault detection system is provided by way of example. The system has five functions: parameter setting, data acquisition, fault diagnosis, database and help. In the interface corresponding to the fault diagnosis function, a Lissajous graph and a support vector regression fitting curve are displayed, as well as a fault result viewing control, a fault degree viewing control and a result retention control.

[0111] In this embodiment, by displaying the real-time Lissajous figure of any reactor and the inclination angle corresponding to the real-time Lissajous figure of any reactor in the system interface of the reactor inter-turn short-circuit fault detection system, as well as displaying the support vector regression fitting curve, the fault status of the reactor can be quickly and intuitively viewed in the system interface.

[0112] In another embodiment, Figure 7 As shown in the figure, a method for identifying inter-turn short-circuit faults in reactors based on Lissajous diagrams and support vector regression is provided. Figure 1 Taking the server 104 in the example as an example, the following steps are included:

[0113] Step S702, obtaining a reactor reconstruction signal set; the reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor; the voltage reconstruction signal and the current reconstruction signal corresponding to any of the reactors are obtained after signal reconstruction of the port voltage signal and the port current signal of the reactor.

[0114] Step S704, generating Lissajous figures corresponding to each of the reactors based on the reactor reconstruction signal set; the Lissajous figure corresponding to any of the reactors represents the variation trend of the voltage waveform and the current waveform of the reactor.

[0115] Step S706: for any of the reactors, determine the inclination angle of the Lissajous figure corresponding to the reactor, and determine the fault degree of the reactor based on the inclination angle.

[0116] Step S708: Use support vector regression to fit the tilt angle and fault degree corresponding to each of the reactors to obtain a support vector regression fitting curve.

[0117] Step S710, determining the inclination angle when the fault degree is a preset degree in the support vector regression fitting curve, and taking the inclination angle when the fault degree is the preset degree as a fault threshold; the fault threshold is used to identify in real time whether any of the reactors has a turn-to-turn short circuit fault.

[0118] Step S712, obtaining a real-time voltage signal and a real-time current signal corresponding to any of the reactors.

[0119] Step S714: generating a real-time Lissajous figure of any of the reactors based on the real-time voltage signal and the real-time current signal corresponding to any of the reactors.

[0120] Step S716: When the inclination angle corresponding to the real-time Lissajous figure of any of the reactors is greater than the fault threshold, it is determined that a turn-to-turn short circuit fault occurs in any of the reactors.

[0121] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a method for identifying inter-turn short-circuit faults of reactors based on Lissajous diagrams and support vector regression described above.

[0122] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0123] Based on the same inventive concept, the embodiment of the present application also provides a device for identifying short-circuit faults between reactors based on Lissajous figures and support vector regression for implementing the method for identifying short-circuit faults between reactors based on Lissajous figures and support vector regression. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the device for identifying short-circuit faults between reactors based on Lissajous figures and support vector regression provided below can be referred to the limitations of the method for identifying short-circuit faults between reactors based on Lissajous figures and support vector regression in the above text, and will not be repeated here.

[0124] In an exemplary embodiment, Figure 8As shown, a device for identifying a reactor inter-turn short-circuit fault based on Lissajous diagrams and support vector regression is provided, comprising: an acquisition module 802, a generation module 804, a determination module 806, a fitting module 808 and an identification module 810, wherein:

[0125] The acquisition module 802 is used to acquire a reactor reconstruction signal set; the reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor; the voltage reconstruction signal and the current reconstruction signal corresponding to any reactor are obtained by reconstructing the port voltage signal and the port current signal of the reactor;

[0126] A generating module 804 is used to generate Lissajous figures corresponding to each reactor based on the reactor reconstruction signal set; the Lissajous figure corresponding to any reactor represents the change trend of the voltage waveform and current waveform of the reactor;

[0127] A determination module 806 is used to determine, for any reactor, a tilt angle of a Lissajous figure corresponding to the reactor, and determine a fault degree of the reactor based on the tilt angle;

[0128] A fitting module 808 is used to fit the tilt angle and fault degree corresponding to each reactor by using support vector regression to obtain a support vector regression fitting curve;

[0129] The identification module 810 is used to determine the inclination angle when the fault degree is a preset degree in the support vector regression fitting curve, and use the inclination angle when the fault degree is a preset degree as the fault threshold; the fault threshold is used to identify in real time whether any inductor has a turn-to-turn short circuit fault.

[0130] In an exemplary embodiment, the acquisition module 802 is specifically used to obtain a set of reactor voltage and current signals; the reactor voltage and current signal set includes a port voltage signal and a port current signal of each reactor; the power frequency component of the port voltage signal and the port current signal of any reactor is extracted to obtain a voltage reconstruction signal and a current reconstruction signal of any reactor; based on the voltage reconstruction signal and the current reconstruction signal of each reactor, a reactor reconstruction signal set is generated.

[0131] In an exemplary embodiment, the acquisition module 802 is specifically used to construct a finite element simulation model of a reactor and obtain simulation condition configuration information; the simulation condition configuration information is configured with simulation conditions for the reactor in a healthy state and simulation conditions under different fault states; different fault states correspond to different fault locations or different fault degrees; based on the different simulation conditions configured by the simulation condition configuration information, the finite element simulation model of the reactor is simulated to obtain a reactor voltage and current simulation signal set; the reactor voltage and current simulation signal set is used as the reactor voltage and current signal set.

[0132] In an exemplary embodiment, the fitting module 808 is specifically configured to use the tilt angle corresponding to each reactor as the dependent variable, the fault degree corresponding to each reactor as the independent variable, and based on the dependent variable and the independent variable, construct an optimization objective and constraint conditions for the support vector regression fitting curve; based on the tilt angle and the fault degree corresponding to each reactor, use the support vector regression method to solve the optimization objective under the condition of satisfying the constraint conditions, and obtain the support vector regression fitting curve.

[0133] In an exemplary embodiment, the device further includes: a real-time recognition module, configured to obtain a real-time voltage signal and a real-time current signal corresponding to any reactor; generate a real-time Lissajous figure of any reactor based on the real-time voltage signal and the real-time current signal corresponding to any reactor; and determine that any reactor has a turn-to-turn short circuit fault when the tilt angle corresponding to the real-time Lissajous figure of any reactor is greater than a fault threshold.

[0134] In an exemplary embodiment, the device further includes: a display module, configured to display the real-time Lissajous figure of any reactor, the tilt angle corresponding to the real-time Lissajous figure of any reactor, and the support vector regression fitting curve in the system interface of the reactor turn-to-turn short circuit fault detection system.

[0135] Each module in the above-mentioned reactor turn-to-turn short circuit fault identification device based on the Lissajous figure and support vector regression can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0136] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the reactor inter-turn short-circuit fault identification data based on Lissajous diagrams and support vector regression. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for identifying a reactor inter-turn short-circuit fault based on Lissajous diagrams and support vector regression is implemented.

[0137] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression. Here, the steps of the method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression can be the steps of the method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression in each of the above-mentioned embodiments.

[0139] In one embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the processor executes the steps of the above-mentioned method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression. Here, the steps of the method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression can be the steps of the method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression in each of the above-mentioned embodiments.

[0140] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the processor executes the steps of the above-mentioned method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression. Here, the steps of the method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression can be the steps of the method for identifying a short-circuit fault between turns of a reactor based on Lissajous figures and support vector regression in each of the above-mentioned embodiments.

[0141] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0142] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0143] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, 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 attached claims.

Claims

1. A method for identifying reactor turn-to-turn short-circuit faults based on Lissajous diagrams and support vector regression, characterized in that: The method comprises: Acquire a reactor reconstruction signal set; the reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor; the voltage reconstruction signal and the current reconstruction signal corresponding to any of the reactors are obtained by reconstructing the port voltage signal and the port current signal of the reactor; Based on the reactor reconstruction signal set, a Lissajous figure corresponding to each of the reactors is generated; the Lissajous figure corresponding to any of the reactors represents a change trend of a voltage waveform and a current waveform of the reactor; For any of the reactors, determining a tilt angle of a Lissajous figure corresponding to the reactor, and determining a fault degree of the reactor based on the tilt angle; Support vector regression is used to fit the tilt angle and fault degree corresponding to each of the reactors to obtain a support vector regression fitting curve; In the support vector regression fitting curve, the inclination angle when the fault degree is a preset degree is determined, and the inclination angle when the fault degree is the preset degree is used as a fault threshold; the fault threshold is used to identify in real time whether any of the reactors has a turn-to-turn short circuit fault.

2. The method according to claim 1, characterized in that The obtaining of the reactor reconstruction signal set comprises: Acquire a reactor voltage and current signal set; the reactor voltage and current signal set includes a port voltage signal and a port current signal of each of the reactors; Extracting the power frequency components of the port voltage signal and the port current signal of any of the reactors to obtain a voltage reconstruction signal and a current reconstruction signal of any of the reactors; The reactor reconstruction signal set is generated based on the voltage reconstruction signal and the current reconstruction signal of each of the reactors.

3. The method according to claim 2, characterized in that The step of obtaining a reactor voltage and current signal set comprises: Constructing a finite element simulation model of a reactor and obtaining simulation condition configuration information; the simulation condition configuration information is configured with simulation conditions for the reactor in a healthy state and simulation conditions in different fault states; different fault states correspond to different fault locations or different fault degrees; Based on different simulation conditions configured by the simulation condition configuration information, the reactor finite element simulation model is simulated to obtain a reactor voltage and current simulation signal set; The reactor voltage and current simulation signal set is used as the reactor voltage and current signal set.

4. The method according to claim 1, characterized in that: The support vector regression is used to fit the tilt angle and fault degree corresponding to each of the reactors to obtain a support vector regression fitting curve, including: Taking the tilt angle corresponding to each of the reactors as a dependent variable, taking the fault degree corresponding to each of the reactors as an independent variable, and constructing an optimization target and constraint conditions for the support vector regression fitting curve based on the dependent variable and the independent variable; Based on the tilt angle and fault degree corresponding to each of the reactors, the optimization target is solved by using a support vector regression method while satisfying the constraint conditions, so as to obtain the support vector regression fitting curve.

5. The method according to claim 1, characterized in that After the step of taking the inclination angle when the fault degree is a preset degree as the fault threshold, the method further comprises: Obtaining a real-time voltage signal and a real-time current signal corresponding to any of the reactors; Based on the real-time voltage signal and the real-time current signal corresponding to any of the reactors, generating a real-time Lissajous figure of any of the reactors; When the inclination angle corresponding to the real-time Lissajous figure of any of the reactors is greater than the fault threshold, it is determined that a turn-to-turn short circuit fault occurs in any of the reactors.

6. The method according to claim 5, characterized in that The method further comprises: In the system interface of the reactor inter-turn short-circuit fault detection system, the real-time Lissajous figure of any of the reactors and the inclination angle corresponding to the real-time Lissajous figure of any of the reactors are displayed, and the support vector regression fitting curve is displayed.

7. A device for identifying inter-turn short-circuit faults of reactors based on Lissajous diagrams and support vector regression, characterized in that: The device comprises: An acquisition module is used to acquire a reactor reconstruction signal set; the reactor reconstruction signal set includes a voltage reconstruction signal and a current reconstruction signal corresponding to each reactor; the voltage reconstruction signal and the current reconstruction signal corresponding to any of the reactors are obtained after signal reconstruction of the port voltage signal and the port current signal of the reactor; A generating module, for generating Lissajous figures corresponding to each of the reactors based on the reactor reconstruction signal set; the Lissajous figures corresponding to any of the reactors represent the change trend of the voltage waveform and the current waveform of the reactor; A determination module, configured to determine, for any of the reactors, an inclination angle of a Lissajous figure corresponding to the reactor, and determine a fault degree of the reactor based on the inclination angle; A fitting module, used for fitting the tilt angle and fault degree corresponding to each of the reactors by using support vector regression to obtain a support vector regression fitting curve; An identification module is used to determine the inclination angle when the fault degree is a preset degree in the support vector regression fitting curve, and use the inclination angle when the fault degree is the preset degree as a fault threshold; the fault threshold is used to identify in real time whether any of the reactors has a turn-to-turn short circuit fault.

8. A reactor turn-to-turn short-circuit fault identification system based on Lissajous diagram and support vector regression, characterized in that: The system includes a first interface for displaying real-time voltage waveforms and real-time current waveforms, a second interface for displaying real-time Lissajous figures and the tilt angles corresponding to the real-time Lissajous figures, and a third interface for processing a reactor voltage and current signal set.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images