CN117033950A - GIS isolating switch mechanical fault on-line diagnosis method and device - Google Patents
GIS isolating switch mechanical fault on-line diagnosis method and device Download PDFInfo
- Publication number
- CN117033950A CN117033950A CN202311291613.0A CN202311291613A CN117033950A CN 117033950 A CN117033950 A CN 117033950A CN 202311291613 A CN202311291613 A CN 202311291613A CN 117033950 A CN117033950 A CN 117033950A
- Authority
- CN
- China
- Prior art keywords
- breakdown
- vfto
- fault
- voltage
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 138
- 238000003745 diagnosis Methods 0.000 title claims abstract description 22
- 230000015556 catabolic process Effects 0.000 claims abstract description 115
- 230000008569 process Effects 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 15
- 238000005070 sampling Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 8
- 238000002955 isolation Methods 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 11
- 230000005540 biological transmission Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000010355 oscillation Effects 0.000 description 4
- 230000001052 transient effect Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3275—Fault detection or status indication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The application relates to a GIS isolating switch mechanical fault on-line diagnosis method and device, wherein the method comprises the following steps: obtaining a VFTO waveform generated in a plurality of normal closing processes of a GIS isolating switch; extracting a voltage breakdown waveform contained in the single VFTO waveform, extracting a residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveform, and generating corresponding characteristic data; normalizing the characteristic data corresponding to all voltage breakdown waveforms contained in the VFTO waveforms to form a training sample set, and training an anomaly detection model; extracting characteristic data of the VFTO waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data; if the duty ratio of the fault data in the data set to be tested exceeds the set threshold value, judging the fault as a fault, and reporting early warning information. The application realizes the on-line diagnosis of the mechanical faults of the GIS isolating switch, is beneficial to early occurrence of potential faults and early warning in time.
Description
Technical Field
The application relates to the technical field of fault diagnosis, in particular to a GIS isolating switch mechanical fault on-line diagnosis method and device based on ultra-fast transient overvoltage (Very fast transient overvoltage, VFTO) residual voltage.
Background
The large-scale and long-distance consumption requirement of high-proportion clean energy promotes the rapid construction of ultra-high voltage transmission engineering in an electric power system. The gas-insulated metal-enclosed switchgear (Gas Insulated Switchgear, GIS) is widely used in ultra-high voltage substations due to its compact structure and reliable operation. The isolating switch is an important unit of the GIS and is divided into a driving motor, a transmission link and a contact, wherein in the switching-on and switching-off process, the driving motor is controlled to brake through the transmission link, and the fixed contact is contacted or separated, so that the live switching of the high-voltage equipment is realized. Because the operating environment is bad and the action is frequent, the GIS isolating switch is easy to generate mechanical faults such as jamming, rotation shaft rust, transmission rod deformation and the like, so that the stroke characteristics of the contact are changed, and serious accidents such as insufficient switching on/off, on-load switching and the like are caused, thereby seriously threatening the safe operation of the power grid.
The existing fault detection method comprises a direct monitoring method and an indirect method. The direct monitoring thought such as an image recognition method and an infrared imaging method is not applicable because the action process of the switch contact is blocked by the GIS sealed shell and is not visible. An automatic detection device and method for the state of a disconnecting switch based on image processing (publication number: CN 110336930A) is characterized in that a shooting ball is additionally arranged in a shell to preprocess a picture, so that a characteristic picture which highlights the disconnecting switch is obtained; detecting and tracking the isolation; and judging the state of the isolating switch according to the tracking condition. However, the GIS internal components are more and mutually shielded, and an observation dead angle area exists, so that the universality of the image processing evaluation method is low.
The indirect method is based on the clear and stable mapping relation between the selected external physical quantity and the contact action. For example, a system and method for on-line detection of a disconnector (publication number: CN105572581 a) achieves on-line detection of a disconnector by converting analog signals including a temperature analog signal, a displacement analog signal, a switching value analog signal, and a current analog signal of a motor of the disconnector into detection light signals. However, in engineering practice, the relationship is susceptible to multiple factors and changes, which greatly limits the accuracy of online diagnosis. For example, the noise sources in the transformer substation are many and the frequency spectrum is wide, and the interference is based on-line monitoring of the vibration sound signals; the transmission rod deformation directly changes the relationship between external physical quantities such as motor current, crank arm angular displacement and the like and the stroke of the contact, so that the monitoring result is inaccurate. Therefore, it is necessary to explore reliable external characterization of the GIS internal contact travel and construct a discrimination feature.
Disclosure of Invention
Aiming at the technical problems existing in the prior art, the application provides a GIS isolating switch mechanical fault on-line diagnosis method and device based on extra-fast transient overvoltage (Very fast transient overvoltage, VFTO) residual voltage, which comprises the steps of firstly, utilizing a VFTO sensor and a high-frequency collector to acquire the waveform digital quantity of the whole process of the VFTO accompanying the action process of the GIS isolating switch; secondly, extracting the whole process waveform into a plurality of single VFTO waveforms, and establishing indicating characteristics of the mechanical state of the GIS isolating switch based on a VFTO generation mechanism; then, constructing a training sample data set based on the VFTO whole-process waveform of the multiple opening and closing processes; because the modeling data set is derived from a GIS isolating switch with normal mechanical state, the training sample set has a very asymmetric problem, and a single-classification support vector machine (One Class support vector machine, OCSVM) model is selected as a to-be-trained discrimination model; finally, the trained identification model is utilized to conduct on-line identification on typical mechanical faults such as jamming, on-load switching and the like of the GIS isolating switch, potential faults of the GIS isolating switch can be found as soon as possible, and the GIS isolating switch has important engineering value.
The technical scheme for solving the technical problems is as follows:
in a first aspect, the application provides an on-line diagnosis method for mechanical faults of a GIS isolating switch, which comprises the following steps:
s100, acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a GIS isolating switch multiple normal opening process or normal closing process;
s200, extracting voltage breakdown waveforms contained in a single-group VFTO full-process discrete digital waveform, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveform, and generating characteristic data corresponding to the single voltage breakdown waveform;
s300, carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in a plurality of groups of VFTO whole-process discrete digital waveforms to form a training sample set and training an anomaly detection model;
s400, extracting and normalizing characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data;
s500, if the duty ratio of the fault data in the data set to be tested exceeds a set threshold value, judging that the fault is a fault, and reporting early warning information.
Further, obtaining a plurality of groups of VFTO whole-process discrete digital waveforms generated in a plurality of normal opening processes or normal closing processes of the GIS isolating switch includes:
acquiring primary side high voltage VFTO signals of a plurality of groups of isolating switches in a normal opening or closing state, and converting the primary side high voltage VFTO signals into low voltage VFTO signals in a fixed proportion;
and sampling the low-voltage VFTO signal at a fixed sampling frequency to obtain a digital discrete value of the whole-process waveform of the VFTO.
Further, extracting a voltage breakdown waveform included in the single-group VFTO full-process discrete digital waveform, and extracting a residual voltage first-order difference value and a breakdown time of the single voltage breakdown waveform, and generating feature data corresponding to the single voltage breakdown waveform, including:
the voltage of two adjacent sampling points in the single-group VFTO whole-process discrete digital waveform is differentiated, when the differential value is higher than a threshold value, arc breakdown is judged, the moment is defined as breakdown moment, and the waveform generated from the moment to the second breakdown moment is defined as a single voltage breakdown waveform;
for any voltage breakdown waveform, recording the breakdown time as a first characteristic quantity, taking the value obtained by subtracting the residual voltage after the last breakdown from the residual voltage of the current breakdown as a second characteristic quantity, and combining the two characteristic quantities as characteristic data of the current voltage breakdown waveform.
Furthermore, the anomaly detection model adopts a single-classification support vector machine, and a classification decision function of the model is obtained after training is completed.
Further, extracting and normalizing characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, inputting the data set to be detected into a trained abnormal detection model to obtain fault data, wherein the data set to be detected is sent into a classification decision function of the abnormal detection model to obtain a decision value, when the function value is 1, the GIS isolating switch is normal operation data, and when the value is-1, the GIS isolating switch is fault data.
Further, if the duty ratio of the fault data in the data set to be tested exceeds the set threshold, determining that the fault is a fault, and reporting early warning information, including: counting the size of fault data samples, calculating the fault number duty ratio according to the following formula,
，
when the fault number duty ratio exceeds a threshold value alpha, judging that the GIS isolating switch has faults in the moving process, otherwise, judging that the GIS isolating switch is normal, and the preferred alpha is 20%.
Further, the method for extracting the residual voltage comprises the following steps: extracting a single voltage breakdown waveform, and taking an average value of voltages of the last m sampling points of the waveform, wherein m is more than or equal to 2, namely the residual voltage of the breakdown.
In a second aspect, the present application provides an on-line diagnosis device for mechanical faults of a GIS isolating switch, including:
the data acquisition module is used for acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a normal switching-off process or a normal switching-on process of the GIS isolating switch for a plurality of times;
the characteristic data generation module is used for extracting voltage breakdown waveforms contained in the single-group VFTO full-process discrete digital waveforms, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveforms, and generating characteristic data corresponding to the single voltage breakdown waveforms;
the data processing and model training module is used for carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in the VFTO whole-process discrete digital waveforms to form a training sample set and training an abnormal detection model;
the fault identification module is used for extracting and normalizing the characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data;
the fault judging module is used for judging whether the duty ratio of the fault data in the data set to be tested exceeds a set threshold value, if so, judging the fault and reporting the early warning information.
In a third aspect, the present application provides an electronic device comprising:
a memory for storing a computer software program;
and the processor is used for reading and executing the computer software program so as to realize the on-line diagnosis method for the mechanical faults of the GIS isolating switch.
In a fourth aspect, the present application provides a non-transitory computer readable storage medium, where a computer software program is stored, where the computer software program, when executed by a processor, implements a method for diagnosing mechanical faults of a GIS disconnector according to the first aspect of the present application.
The beneficial effects of the application are as follows: the on-line diagnosis of the mechanical faults of the GIS isolating switch is realized, the potential faults of the GIS isolating switch can be generated as early as possible, early warning is timely carried out, and the GIS isolating switch has important engineering value.
Drawings
FIG. 1 is a schematic flow chart of a GIS isolating switch mechanical fault on-line diagnosis method provided by the embodiment of the application;
fig. 2 is a schematic diagram of a single VFTO waveform according to an embodiment of the present application;
fig. 3 is a schematic diagram of fitting characteristic data of an isolating switch in a normal state according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an on-line diagnosis device for mechanical faults of a GIS isolation switch according to an embodiment of the present application;
fig. 5 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the present application;
fig. 6 is a schematic diagram of an embodiment of a computer readable storage medium according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present application, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
As shown in fig. 1, an embodiment of the present application provides an on-line diagnosis method for mechanical faults of a GIS isolation switch, including:
s100, acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a GIS isolating switch multiple normal opening process or normal closing process.
In this embodiment, the method is explained by taking the VFTO whole-process discrete digital waveform generated in the closing process as an example.
Firstly, accumulating to obtain primary side high-voltage VFTO signals of a plurality of groups of isolating switches in a normal closing state, and converting the primary side high-voltage VFTO signals into low-voltage analog signals according to a fixed proportion by utilizing a VFTO sensor; then, converting the low-voltage analog signal into a digital signal by using a high-frequency collector to obtain the discrete digital quantity of the VFTO whole-process waveform; the sampling rate of the high-frequency collector is not lower than 500MS/s, and preferably, the sampling rate is 625MS/s.
S200, extracting voltage breakdown waveforms contained in the single-group VFTO full-process discrete digital waveforms, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveforms, and generating characteristic data corresponding to the single voltage breakdown waveforms.
In the GIS isolating switch, the calculation formula of the critical breakdown voltage at the two ends of the contact is as follows:
（1）
in the method, in the process of the application,is the critical breakdown voltage of the switch gap; />For electric field utilization factor +.>Representing the roughness coefficient of the electrode surface, wherein the value is 0.5-0.8, and the engineering value is less than 0.7; e (E) dt Engineering breakdown field strength of SF6 gas; l is the switch contact gap.
Due to the formula (1)、K f E and E dt All are constants, and are characterized by adopting a constant K, so that the correlation relationship between breakdown voltage and contact opening distance can be obtained, as shown in the formula (2).
（2）
In the method, in the process of the application,in order to obtain the breakdown voltage at the breakdown time t, K represents the withstand voltage of the unit length of the switch gap, and L (t) is the gap between the movable contact and the fixed contact of the switch at the breakdown time t.
There is a relationship shown in the formula (3) between the contact stroke D (t) and the opening distance L (t).
（3）
In the formula, L is the contact opening distance at the starting time of closing.
According to the formula (3), the breakdown voltage time sequence quantity is strongly related to the contact travel, so that characteristic parameters reflecting the breakdown voltage time sequence quantity are constructed based on the VFTO waveform, and the contact travel can be represented.
Based on the theory above, this step can be broken down into the following:
s201, decomposing the VFTO whole process waveform into a plurality of single VFTO waveforms.
Multiple breaks occur during one operation of the GIS disconnector, thus, its accompanying VFTO overall process discrete digital waveform contains multiple single voltage breakdown waveforms. In the single-group VFTO whole-process discrete digital waveform, difference is carried out between two adjacent sampling points:
（4）
when the differential value Q is higher than the threshold value C max When an arc breakdown is judged to occur, defining the moment as the breakdown moment, and defining the moment toThe waveform generated at the second breakdown moment is a single voltage breakdown waveform. Accordingly, a plurality of single voltage breakdown waveforms contained in the VFTO whole-process discrete digital waveform can be extracted.
S202, extracting characteristic values.
As shown in FIG. 2, the waveform of the load side VFTO of single breakdown is characterized by an obvious oscillation process, mainly including waveform characteristic parameters such as breakdown voltage, peak value, duration, residual voltage and the like, and after the breakdown of a gap occurs, the voltage of the load side is changed from an initial value U t The voltage of the residual charge after the last breakdown rises rapidly, reaches a peak value after high-frequency oscillation, and the high-frequency oscillation amplitude continuously decays after the duration T until the next breakdown.
Therefore, the breakdown voltage thereof is calculated as follows:
（5）
in the method, in the process of the application,for breakdown voltage, U s To break down the power supply side voltage, U t The load side residual voltage is the breakdown time.
Compared with the interval time between two adjacent breakdown occurrences, the breakdown duration T is extremely short, and the leakage resistance of the no-load bus in the GIS is very large, and the decay time is long, so that the residual charge in the breakdown duration is considered to be not diffused, and the load side residual voltage is similar to the source side breakdown voltage. Therefore, it is proposed to replace the power supply side voltage with the load side residual voltage after the breakdown duration is over to construct the load side residual voltage time sequence first order difference characteristic U LDIFE As shown in formula (6).
（6）
Wherein t is 0 The initial time of single breakdown is represented, T is the oscillation time of the breakdown waveform, U L (t 0 ) For corresponding time periodsLoad side VFTO waveform value, U LDIFE (t 0 ) At t 0 Characteristic values at the time.
Is available on healdsAccordingly, the breakdown time of all voltage breakdown waveforms of the VFTO whole-process discrete digital waveform generated in the single closing process is extracted as a first characteristic quantity, and the set of normal data is assumed to be +.>. And taking the last several points in the single voltage breakdown process to calculate the voltage average value, namely the residual voltage. The voltage average is calculated in this embodiment from the last 10 to 20 points in the single voltage breakdown process. The value obtained by subtracting the residual voltage after the last breakdown from the residual voltage of the single breakdown is used as a second characteristic quantity, and the set of normal data is assumed to be. Finally, the feature of the following formula (7) is constructed as a feature quantity for discriminating the change in the contact stroke characteristic.
（7）
The scatter plot and the fitted curve are shown in fig. 3.
And S300, carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in the VFTO whole-process discrete digital waveforms to form a training sample set and training an anomaly detection model. In this embodiment, a single-classification support vector machine (OCSVM) model is used as the anomaly detection model. The method specifically comprises the following substeps:
s301, normalizing the characteristic data to generate a support vector X S 。
The linear transformation formula is as follows:
（8）
in summary, training feature normal sample data capable of obtaining OCSVM classification model isAnd they are classified as a class, with a label of 1.
S302, training an OCSVM classification model.
(1) Only two GIS isolating switch state characteristic quantities are contained in the training sample, so that the expression of the OCSVM hyperplane is as follows:
（9）
in the method, in the process of the application,and->A normal vector and an offset term representing the hyperplane, respectively; />Representing a mapping of samples in a high-dimensional space;
(2) in order to separate the sample points from the origin as far as possible, the single-classification support vector machine is simplified into a quadratic programming problem, and then the minimum surrounding curve optimization problem of the single-classification support vector machine is expressed as follows:
（10）
in the method, in the process of the application,for regularization parameters, the value is [0,1 ] which is related to the number of support vectors]；/>Training data set size;is a relaxation variable;
(3) by combining the theory, the optimization problem shown in the following formula is obtained by calculation through the Lagrangian multiplier method:
（11）
wherein,an n-order kernel function matrix; />Is Lagrangian multiplier, X i ，X j Respectively representing a first feature quantity and a second feature quantity, i=j;
(4) optimization (11) based on support vector X S Obtaining the offset：
（12）
(5) After training is completed, obtaining an enclosing curve and a classification decision function of a corresponding training sample, as shown in formula (13):
（13）。
s400, extracting and normalizing the characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data.
It should be noted here that the extraction method of the characteristic data of the VFTO full-process discrete digital waveform to be detected is consistent with the training data set generation method.
And (3) sending the feature data to be detected into an OCSVM model classification decision function shown in a formula (13) to obtain a decision value, wherein when the function value is 1, the GIS isolating switch is normal operation data, and when the value is-1, the GIS isolating switch is fault data.
S500, when the duty ratio of fault data in a data sample to be tested exceeds a set threshold value, judging that the fault is a fault, and reporting early warning information.
And (3) counting the size of fault data samples, calculating the fault number duty ratio according to the formula (14), and judging that the GIS isolating switch is faulty in the moving process when the fault number duty ratio exceeds a threshold value alpha, otherwise, judging that the GIS isolating switch is normal, and the preferred alpha is 20%.
（14）
It should be understood that, because voltage breakdown phenomena are generated in both the opening and closing processes, and the specifically collected VFTO whole-process discrete digital waveforms can be used for performing on-line diagnosis of mechanical faults of the GIS isolation switch through the method, a method flow for performing on-line diagnosis of mechanical faults of the GIS isolation switch by adopting the VFTO whole-process discrete digital waveforms generated in the opening process is not described herein.
As shown in fig. 4, an embodiment of the present application provides an on-line diagnosis device for mechanical failure of a GIS isolation switch, including:
the data acquisition module is used for acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a normal switching-off process or a normal switching-on process of the GIS isolating switch for a plurality of times;
the characteristic data generation module is used for extracting voltage breakdown waveforms contained in the single-group VFTO full-process discrete digital waveforms, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveforms, and generating characteristic data corresponding to the single voltage breakdown waveforms;
the data processing and model training module is used for carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in the VFTO whole-process discrete digital waveforms to form a training sample set and training an abnormal detection model;
the fault identification module is used for extracting and normalizing the characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data;
the fault judging module is used for judging whether the duty ratio of the fault data in the data set to be tested exceeds a set threshold value, if so, judging the fault and reporting the early warning information.
Referring to fig. 5, fig. 5 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the application. As shown in fig. 5, an embodiment of the present application provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored on the memory 510 and executable on the processor 520, wherein the processor 520 executes the computer program 511 to implement the following steps:
s100, acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a GIS isolating switch multiple normal opening process or normal closing process;
s200, extracting voltage breakdown waveforms contained in a single-group VFTO full-process discrete digital waveform, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveform, and generating characteristic data corresponding to the single voltage breakdown waveform;
s300, carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in a plurality of groups of VFTO whole-process discrete digital waveforms to form a training sample set and training an anomaly detection model;
s400, extracting and normalizing characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data;
s500, if the duty ratio of the fault data in the data set to be tested exceeds a set threshold value, judging that the fault is a fault, and reporting early warning information.
Referring to fig. 6, fig. 6 is a schematic diagram of an embodiment of a computer readable storage medium according to an embodiment of the application. As shown in fig. 6, the present embodiment provides a computer-readable storage medium 600 having stored thereon a computer program 611, which computer program 611 when executed by a processor implements the steps of:
s100, acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a GIS isolating switch multiple normal opening process or normal closing process;
s200, extracting voltage breakdown waveforms contained in a single-group VFTO full-process discrete digital waveform, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveform, and generating characteristic data corresponding to the single voltage breakdown waveform;
s300, carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in a plurality of groups of VFTO whole-process discrete digital waveforms to form a training sample set and training an anomaly detection model;
s400, extracting and normalizing characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data;
s500, if the duty ratio of the fault data in the data set to be tested exceeds a set threshold value, judging that the fault is a fault, and reporting early warning information.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The on-line diagnosis method for the mechanical faults of the GIS isolating switch is characterized by comprising the following steps of:
s100, acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a GIS isolating switch multiple normal opening process or normal closing process;
s200, extracting voltage breakdown waveforms contained in a single-group VFTO full-process discrete digital waveform, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveform, and generating characteristic data corresponding to the single voltage breakdown waveform;
s300, carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in a plurality of groups of VFTO whole-process discrete digital waveforms to form a training sample set and training an anomaly detection model;
s400, extracting and normalizing characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data;
s500, if the duty ratio of the fault data in the data set to be tested exceeds a set threshold value, judging that the fault is a fault, and reporting early warning information.
2. The method of claim 1, wherein obtaining a plurality of sets of VFTO whole-process discrete digital waveforms generated by a GIS isolation switch in a plurality of normal opening processes or a normal closing process comprises:
acquiring primary side high voltage VFTO signals of a plurality of groups of isolating switches in a normal opening or closing state, and converting the primary side high voltage VFTO signals into low voltage VFTO signals in a fixed proportion;
and sampling the low-voltage VFTO signal at a fixed sampling frequency to obtain a digital discrete value of the whole-process waveform of the VFTO.
3. The method of claim 1, wherein extracting the voltage breakdown waveforms included in the single set of VFTO full-process discrete digital waveforms, and extracting the residual voltage first order difference and the breakdown time of the single voltage breakdown waveforms, and generating the feature data corresponding to the single voltage breakdown waveforms, comprises:
the voltage of two adjacent sampling points in the single-group VFTO whole-process discrete digital waveform is differentiated, when the differential value is higher than a threshold value, arc breakdown is judged, the moment is defined as breakdown moment, and the waveform generated from the moment to the second breakdown moment is defined as a single voltage breakdown waveform;
for any voltage breakdown waveform, recording breakdown time as a first characteristic quantity, enabling a value obtained by subtracting the residual voltage after the last breakdown from the residual voltage of the current breakdown to be used as a second characteristic quantity, combining the two characteristic quantities to be used as characteristic data of the current voltage breakdown waveform, and recording as follows:
；
wherein t is i Represents the breakdown time of the ith voltage breakdown, i.e. the first characteristic quantity, U LDIFE (t i ) The second characteristic amount is a value obtained by subtracting the residual voltage after the i-1 th breakdown from the participation voltage of the i-th voltage breakdown.
4. The method of claim 1, wherein the anomaly detection model employs a single classification support vector machine, and the classification decision function of the model is obtained after training is completed.
5. The method of claim 4, wherein extracting feature data of the VFTO to be detected in the whole process discrete digital waveform and normalizing the feature data to generate a data set to be detected, and inputting the data set to a trained anomaly detection model to obtain fault data, and further comprising sending the data set to be detected to a classification decision function of the anomaly detection model to obtain a decision value, wherein when the function value is 1, the GIS isolating switch is normal operation data, and when the function value is-1, the GIS isolating switch is fault data.
6. The method of claim 1, wherein if the duty ratio of the fault data in the data set to be tested exceeds the set threshold, determining that the fault is a fault, and reporting the early warning information, including: counting the size of fault data samples, calculating the fault number duty ratio according to the following formula,
，
and when the fault number duty ratio exceeds a threshold value, judging that the GIS isolating switch has faults in the moving process, and otherwise, judging that the GIS isolating switch is normal.
7. A method according to claim 3, wherein the residual voltage extraction method comprises: extracting a single voltage breakdown waveform, and taking an average value of voltages of the last m sampling points of the waveform, wherein m is more than or equal to 2, namely the residual voltage of the breakdown.
8. The utility model provides a GIS isolator mechanical failure on-line diagnosis device which characterized in that includes:
the data acquisition module is used for acquiring a plurality of groups of VFTO whole-process discrete digital waveforms generated in a normal switching-off process or a normal switching-on process of the GIS isolating switch for a plurality of times;
the characteristic data generation module is used for extracting voltage breakdown waveforms contained in the single-group VFTO full-process discrete digital waveforms, extracting residual voltage first-order difference quantity and breakdown time of the single voltage breakdown waveforms, and generating characteristic data corresponding to the single voltage breakdown waveforms;
the data processing and model training module is used for carrying out normalization processing on characteristic data corresponding to all voltage breakdown waveforms contained in the VFTO whole-process discrete digital waveforms to form a training sample set and training an abnormal detection model;
the fault identification module is used for extracting and normalizing the characteristic data of the VFTO full-process discrete digital waveform to be detected, generating a data set to be detected, and inputting the data set to a trained abnormal detection model to obtain fault data;
the fault judging module is used for judging whether the duty ratio of the fault data in the data set to be tested exceeds a set threshold value, if so, judging the fault and reporting the early warning information.
9. An electronic device, comprising:
a memory for storing a computer software program;
and the processor is used for reading and executing the computer software program so as to realize the GIS isolating switch mechanical fault on-line diagnosis method as claimed in any one of claims 1 to 7.
10. A non-transitory computer readable storage medium, characterized in that the storage medium has stored therein a computer software program which, when executed by a processor, implements a GIS disconnector mechanical fault online diagnosis method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311291613.0A CN117033950B (en) | 2023-10-08 | 2023-10-08 | GIS isolating switch mechanical fault on-line diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311291613.0A CN117033950B (en) | 2023-10-08 | 2023-10-08 | GIS isolating switch mechanical fault on-line diagnosis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117033950A true CN117033950A (en) | 2023-11-10 |
| CN117033950B CN117033950B (en) | 2023-12-26 |
Family
ID=88635844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311291613.0A Active CN117033950B (en) | 2023-10-08 | 2023-10-08 | GIS isolating switch mechanical fault on-line diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117033950B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2747094A1 (en) * | 2012-12-21 | 2014-06-25 | ABB Technology AG | Very fast transient overvoltage attenuator |
| CN106846316A (en) * | 2017-02-10 | 2017-06-13 | 云南电网有限责任公司电力科学研究院 | A kind of GIS inside typical defect automatic distinguishing method for image |
| CN108647469A (en) * | 2018-05-28 | 2018-10-12 | 武汉理工大学 | A kind of mathematic(al) representation approximating method of TEV mass datas |
| CN109188258A (en) * | 2018-07-17 | 2019-01-11 | 国网浙江省电力有限公司检修分公司 | The high-voltage circuitbreaker feature extraction and classification method being electrically coupled based on vibration |
| CN110967184A (en) * | 2019-12-03 | 2020-04-07 | 合肥工业大学 | Gearbox fault detection method and system based on vibration signal distribution characteristic recognition |
| CN111413641A (en) * | 2020-04-03 | 2020-07-14 | 合肥凯高电气设备有限公司 | Microcomputer relay protection method using HHT transient characteristic quantity detection |
| US20210167584A1 (en) * | 2019-11-29 | 2021-06-03 | Electric Power Science & Research Institute Of State Grid Tianjin Electric Power Company | Gis mechanical fault diagnosis method and device |
| CN113191192A (en) * | 2021-03-25 | 2021-07-30 | 云南电网有限责任公司玉溪供电局 | Breaker fault detection method based on wavelet analysis and fuzzy neural network algorithm |
| CN114113995A (en) * | 2021-10-29 | 2022-03-01 | 河南平高电气股份有限公司 | Method and system for detecting mechanical fault of isolating switch for GIS |
| WO2023138337A1 (en) * | 2022-01-18 | 2023-07-27 | 华为技术有限公司 | Motor fault detection method and apparatus |
-
2023
- 2023-10-08 CN CN202311291613.0A patent/CN117033950B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2747094A1 (en) * | 2012-12-21 | 2014-06-25 | ABB Technology AG | Very fast transient overvoltage attenuator |
| CN106846316A (en) * | 2017-02-10 | 2017-06-13 | 云南电网有限责任公司电力科学研究院 | A kind of GIS inside typical defect automatic distinguishing method for image |
| CN108647469A (en) * | 2018-05-28 | 2018-10-12 | 武汉理工大学 | A kind of mathematic(al) representation approximating method of TEV mass datas |
| CN109188258A (en) * | 2018-07-17 | 2019-01-11 | 国网浙江省电力有限公司检修分公司 | The high-voltage circuitbreaker feature extraction and classification method being electrically coupled based on vibration |
| US20210167584A1 (en) * | 2019-11-29 | 2021-06-03 | Electric Power Science & Research Institute Of State Grid Tianjin Electric Power Company | Gis mechanical fault diagnosis method and device |
| CN110967184A (en) * | 2019-12-03 | 2020-04-07 | 合肥工业大学 | Gearbox fault detection method and system based on vibration signal distribution characteristic recognition |
| CN111413641A (en) * | 2020-04-03 | 2020-07-14 | 合肥凯高电气设备有限公司 | Microcomputer relay protection method using HHT transient characteristic quantity detection |
| CN113191192A (en) * | 2021-03-25 | 2021-07-30 | 云南电网有限责任公司玉溪供电局 | Breaker fault detection method based on wavelet analysis and fuzzy neural network algorithm |
| CN114113995A (en) * | 2021-10-29 | 2022-03-01 | 河南平高电气股份有限公司 | Method and system for detecting mechanical fault of isolating switch for GIS |
| WO2023138337A1 (en) * | 2022-01-18 | 2023-07-27 | 华为技术有限公司 | Motor fault detection method and apparatus |
Non-Patent Citations (2)
| Title |
|---|
| WANG LIHUI.ET AL: ""Measurement of transient electromagnetic coupling and interference caused by disconnector operation in substation"", 《ELSEVIER》 * |
| 王希: ""特高压GIS变电站中VFTO特性及影响因素研究"", 《山东电力技术》, vol. 42, no. 210 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117033950B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101574615B1 (en) | A partial discharge monitoring and diagnosis system for power devices by using signal detection based on statistical phase-angle patterns | |
| CN112069930A (en) | Vibration signal processing method and device for improving GIS equipment fault diagnosis accuracy | |
| Wang et al. | Few-shot transfer learning with attention mechanism for high-voltage circuit breaker fault diagnosis | |
| CN108805107B (en) | Method for identifying partial discharge defects in GIS based on PRPS signal | |
| CN110647924B (en) | GIS equipment state evaluation method based on support vector description and K-nearest neighbor algorithm | |
| CN112816838B (en) | GIS equipment defect diagnosis device and method based on FFT, VMD and LS-SVM | |
| CN113379252A (en) | Bayesian network high-voltage switch cabinet health system evaluation method based on multi-scale arrangement entropy | |
| CN113745049B (en) | Vacuum degree monitoring method and system in vacuum arc extinguish chamber | |
| CN117269655B (en) | Transformer substation power equipment temperature anomaly monitoring method, system, terminal and medium | |
| CN117033950B (en) | GIS isolating switch mechanical fault on-line diagnosis method and device | |
| CN117094705B (en) | Method, system and equipment for predicting defects of high-voltage switch cabinet | |
| CN117409529B (en) | Multi-scene electrical fire on-line monitoring method and system | |
| CN115343579B (en) | Power grid fault analysis method and device and electronic equipment | |
| Qiu et al. | State assessment of key equipment of microgrid based on multi-source data fusion method | |
| CN116298725A (en) | Fault arc detection method, system and storage medium | |
| CN109917245B (en) | Ultrasonic detection partial discharge signal mode identification method considering phase difference | |
| Shang et al. | Mechanical fault diagnosis system based on acoustic feature analysis in gas insulated switchgear | |
| Cai et al. | Reviews of research on mechanical fault diagnosis in GIS | |
| CN116184141B (en) | Gas insulation equipment fault diagnosis method and system | |
| Gao et al. | Research on Thermal-Acoustic Fusion Diagnosis of GIS Equipment Defects Based on Improved DS Evidence Theory | |
| CN115166445A (en) | Method and equipment for identifying insulation defects of epoxy resin current transformer and storage medium | |
| Yue et al. | A Fault Diagnosis Method of GIS High Voltage Isolation Switch Based on FA-SVM | |
| Fault et al. | Check for Feature Fusion Based IPSO-LSSVM Fault Diagnosis of On-Load Tap Changers Honghua Xu, Laibi Yin, Ziqiang Xu, Qian Xin, and Mengjie Lv State Grid Nanjing Power Supply Company, Nanjing 320105, China | |
| Wu et al. | GIS Fault Diagnosis Method Based on Multi-Source Feature Dual Decision Hybrid Classification Network | |
| Yang et al. | Research on GIS partial discharge light measuring method based on Fluorescent fiber sensing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |