CN114117923A - High-voltage parallel reactor state judgment system and method based on chaotic feature space - Google Patents

High-voltage parallel reactor state judgment system and method based on chaotic feature space Download PDF

Info

Publication number
CN114117923A
CN114117923A CN202111440545.0A CN202111440545A CN114117923A CN 114117923 A CN114117923 A CN 114117923A CN 202111440545 A CN202111440545 A CN 202111440545A CN 114117923 A CN114117923 A CN 114117923A
Authority
CN
China
Prior art keywords
chaotic
state
characteristic
vibration signal
reactor
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.)
Pending
Application number
CN202111440545.0A
Other languages
Chinese (zh)
Inventor
侯鹏飞
马宏忠
李楠
崔嘉佳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hohai University HHU
Original Assignee
Hohai University HHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hohai University HHU filed Critical Hohai University HHU
Priority to CN202111440545.0A priority Critical patent/CN114117923A/en
Publication of CN114117923A publication Critical patent/CN114117923A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/08—Computing arrangements based on specific mathematical models using chaos models or non-linear system models
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Algebra (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Nonlinear Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Housings And Mounting Of Transformers (AREA)

Abstract

The invention discloses a chaos characteristic space-based high-voltage shunt reactor state judgment system and method in the technical field of intelligent substation power equipment fault diagnosis and state detection, and the chaos characteristic space-based high-voltage shunt reactor state judgment system and method comprises the following steps: acquiring a vibration signal on the surface of a reactor box body; judging whether the vibration signal has chaotic characteristics; when the vibration signal has the chaos characteristic, calculating a multi-chaos characteristic value of the vibration signal; projecting the multiple chaotic characteristic values to multiple chaotic characteristic identification spaces; and judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space. According to the invention, the on-line operation monitoring and diagnosis of the high-voltage shunt reactor are realized by projecting the multiple chaotic characteristic values of the vibration signal to the multiple chaotic characteristic identification space.

Description

High-voltage parallel reactor state judgment system and method based on chaotic feature space
Technical Field
The invention relates to a chaotic feature space-based high-voltage shunt reactor state judgment system and method, and belongs to the technical field of intelligent substation power equipment fault diagnosis and state detection.
Background
The high-voltage shunt reactor is used as important power equipment in a power system, mainly plays a role in reactive power compensation and voltage stabilization, and the safety and the stability of the high-voltage shunt reactor are important for the safe and stable operation of a power grid. Under the action of mechanical force or electromagnetic force, the internal winding and iron core structure of the high-voltage parallel reactor are easy to change, such as winding looseness, winding deformation, winding bulge, iron core looseness, abrasion among silicon steel sheets and the like, which causes great hidden dangers to the safe and stable operation of the reactor, so that the detection technology of the mechanical state of the internal winding and the iron core of the reactor is necessary to be researched, the change of the internal mechanical state of the reactor is timely mastered and found, and the method has important significance to the safe and stable operation of the high-voltage reactor.
The vibration signal of the high-voltage shunt reactor in the running state presents remarkable nonlinear characteristics and contains rich state information, and the change of the mechanical state of the internal winding and the iron core can be effectively reflected by the vibration signal of the box body. However, in an early stage of a latent mechanical fault occurring in the winding and the core component, a weak fault characteristic capable of reflecting a change in the internal mechanical state of the reactor is easily covered by a strong background noise due to an influence of a substation field environment, and when a plurality of mechanical faults or mixed faults occur in the reactor, there may be a case of coupling or weakening, and it is difficult to accurately extract a fault characteristic amount.
The method for extracting the vibration signal features comprises the following steps: time domain analysis, empirical wavelet transform, wavelet analysis, hilbert-yellow transform, empirical mode decomposition, etc., which are mostly based on linear theory, are prone to have problems of end effect, energy leakage, mode aliasing, etc., when applied to nonlinear signal processing, and seriously affect the accuracy of feature extraction. In contrast, nonlinear time domain analysis methods, such as fractal technology, chaos theory, phase space reconstruction and the like, can well describe the essential characteristics and the internal rules of nonlinear vibration signals. Based on the method, the characteristic quantity of the reactor vibration signal is extracted by adopting the multiple chaotic characteristic indexes, and a multiple chaotic characteristic identification space with practical application value is constructed.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a high-voltage shunt reactor state judgment system and method based on a chaotic characteristic space, and realizes online operation monitoring and diagnosis of a high-voltage shunt reactor by projecting multiple chaotic characteristic values of a vibration signal to a chaotic characteristic identification space.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the invention provides a method for judging the state of a high-voltage shunt reactor based on a chaotic feature space, which comprises the following steps:
acquiring a vibration signal on the surface of a reactor box body;
judging whether the vibration signal has chaotic characteristics;
when the vibration signal has the chaos characteristic, calculating a multi-chaos characteristic value of the vibration signal;
projecting the multiple chaotic characteristic values to multiple chaotic characteristic identification spaces;
and judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space.
Further, judging whether the vibration signal has the chaotic characteristic includes:
calculating a K entropy value of the vibration signal by a correlation integral method;
responding to the fact that the K entropy value is not larger than 0, and the vibration signal does not have the chaotic characteristic;
responding to the fact that the K entropy value is larger than 0, and the vibration signal has a chaotic characteristic;
when the vibration signal has the chaos characteristic, the multi-chaos characteristic value of the vibration signal is calculated, and the method comprises the following steps:
and calculating the correlation dimension of the vibration signal through an improved G-P algorithm, and solving the maximum Lyapunov index of the vibration signal through a small data volume method, wherein the multiple chaos eigenvalues comprise the maximum Lyapunov index, a K entropy value and the correlation dimension.
Further, the improved G-P algorithm includes a recurrence formula, which is:
Figure BDA0003382682760000031
Figure BDA0003382682760000032
Figure BDA0003382682760000033
wherein r isijIs Euclidean distance, x (i) is vibration signal time sequence, and m is embedding dimension; τ is the delay time, Xi (m)I-th time series vector of m-dimensional space, Xj (m)A j-th time sequence vector of an m-dimensional space, wherein i and j are the i and j moments respectively;
Figure BDA0003382682760000034
Figure BDA0003382682760000035
Figure BDA0003382682760000036
where C (m, r) is the correlation function, D (m) is the correlation dimension, H (x) is the step function, r is the critical distance, N is the time series length, and x is x (i).
Furthermore, the maximum Lyapunov index, the K entropy and the correlation dimension in the multi-chaos feature identification space are respectively used as an x axis, a y axis and a z axis, and all coordinate axes are arranged in sequence.
Further, the step of judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space comprises the following steps:
judging whether the multiple chaotic characteristic index values are all in a multiple chaotic characteristic index threshold range corresponding to a certain state in a multiple chaotic characteristic identification space;
when the multi-chaos characteristic index values are all in the range of the multi-chaos characteristic index threshold corresponding to a certain state, determining that the reactor state is the reactor state corresponding to the multi-chaos characteristic index threshold;
and when the multiple chaotic characteristic index values are not in the multiple chaotic characteristic index threshold range corresponding to a certain state, determining that the state of the reactor is a new fault.
Further, the multi-chaotic characteristic index threshold range is determined by dividing in a characteristic identification space after repeatedly calculating chaotic characteristic values of the vibration signals in the same state at different time periods.
Further, the reactor state comprises a normal state of a reactor winding iron core, a 50% axial looseness state of the winding iron core, a 100% axial looseness state of the winding iron core, a 30% radial looseness state of the winding iron core, a 60% radial looseness state of the winding iron core and a 100% radial looseness state of the winding iron core.
In a second aspect, the present invention provides a chaos feature space-based high-voltage parallel reactor state determination system, including:
the signal acquisition module: the method comprises the steps of obtaining a vibration signal of the surface of a reactor box body;
a chaotic characteristic judgment module: the chaotic signal generator is used for judging whether the vibration signal has chaotic characteristics or not;
a chaotic characteristic calculation module: the device is used for responding to the fact that the vibration signal has the chaos characteristic, and calculating a multi-chaos characteristic value of the vibration signal;
a feature projection module: the system is used for projecting multiple chaotic characteristic values to multiple chaotic characteristic identification spaces;
a state determination module: the method is used for judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space.
In a third aspect, the invention provides a high-voltage shunt reactor state judgment device based on a chaotic characteristic space, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any of the above.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of any of the methods described above.
Compared with the prior art, the invention has the following beneficial effects:
according to the mixed-action characteristic of the vibration signal of the reactor, the invention utilizes the advantage that the multiple chaotic characteristic indexes are sensitive to the weak mechanical fault of the iron core of the winding in the reactor, and after characteristic quantity extraction, the multiple chaotic characteristic space is utilized to identify the mechanical fault of the iron core of the winding of the reactor, and the online fault identification and diagnosis can be completed without supervised learning and a large amount of training data, so that the invention has higher fault identification capability. The method can effectively diagnose the mechanical state fault of the iron core winding of the high-voltage parallel reactor, improves the reliability and safety of the operation of the reactor, and has important theoretical and practical engineering application values.
Drawings
Fig. 1 is a flow chart of online diagnosis of mechanical faults of a high-voltage shunt reactor winding core according to an embodiment of the invention;
FIG. 2 is a layout diagram of a vibration measuring point on the surface of a reactor according to a first embodiment of the present invention;
FIG. 3 is a time domain diagram of a vibration signal at the No. 4 measuring point on the top surface of the reactor provided in the first embodiment of the present invention in different states;
fig. 4 is a calculation result diagram of a maximum Lyapunov index, a K entropy and an association dimension of multiple chaos indexes provided in the first embodiment of the present invention;
fig. 5 is a mechanical fault diagram of a multi-chaotic feature space recognition reactor winding core according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
the method and the device have the advantages that the multi-chaos characteristic indexes are sensitive to weak mechanical faults of the iron core of the winding in the reactor, and the existence of the latent faults of the iron core of the winding in the reactor can be accurately identified. The vibration acceleration monitoring sensor is arranged on the surface of the reactor box body, and vibration signals in a running state are collected. In general, a vibration signal of the reactor has a chaotic characteristic and presents an obvious nonlinear characteristic. The chaos theory can well describe the essential characteristics and the intrinsic law of the nonlinear vibration signal. In chaos theory, the maximum Lyapunov exponent, the K entropy and the correlation dimension are generally used for quantitatively calculating the chaos characteristic of a signal.
According to the method, on the basis of judging the chaotic characteristic of the vibration signal of the reactor, a plurality of chaotic characteristic index values are calculated, and the chaotic characteristic of the vibration signal is extracted.
Due to the fact that the physical significance of a single chaotic characteristic index is limited, and the contained characteristic information quantity is single, the effect of the chaotic theory cannot be fully shown. Based on the method, a multi-chaos feature identification space is constructed by the maximum Lyapunov index, the K entropy and the correlation dimension, and different states of loosening of the reactor winding iron core are identified. According to the invention, the threshold value ranges of different states are defined by calculating the fluctuation ranges of the vibration signals corresponding to the chaos index values in different states, so that the diagnosis of the mechanical fault of the reactor winding iron core is realized.
In the invention, the condition that the reactor fault samples are difficult to obtain, belong to parameters of small samples and are difficult to supervise and learn is considered, in addition, the vibration signal analysis has the characteristics of nonlinear and high-dimensional modes, a multi-chaotic characteristic identification space is selected for classification and identification, the supervised learning is not needed, and the method is particularly suitable for equipment fault diagnosis with few fault samples. Therefore, the invention provides a multi-chaotic characteristic identification space for diagnosing the mechanical fault of the reactor winding iron core. The specific flow chart refers to the attached figure 1 of the specification, and the specific steps are as follows:
step 1: acquiring a surface vibration signal of the electric reactor box body: arranging monitoring points of a vibration acceleration sensor, and setting sampling frequency and sampling time of a data acquisition instrument;
step 2: judging the chaotic characteristic of the vibration signal of the reactor: calculating a K entropy value (Kolmogorov entropy value) of the vibration signal by using a correlation integral method, and judging the chaotic characteristic of the vibration signal of the reactor by using the K entropy value;
and step 3: solving chaotic characteristic indexes: calculating the correlation dimension of the vibration signal by adopting an improved G-P algorithm, and solving the maximum Lyapunov index of the vibration signal by utilizing a small data volume method;
and 4, step 4: establishing a chaotic feature identification space: constructing a multi-chaos characteristic identification space by taking the maximum Lyapunov index, the K entropy value and the correlation dimension as vector coordinates, and projecting the multi-chaos characteristic values of the reactor vibration signal in different states into the identification space;
and 5: setting a threshold value: repeatedly calculating the chaotic characteristic values of the vibration signals in the same state at different time periods, and delimiting threshold ranges of different chaotic indexes in corresponding states in a characteristic identification space;
step 6: and (3) fault classification and identification: and classifying the faults by using the set threshold range, wherein the faults are known fault types if the faults are within the defined threshold range, and the faults are unknown novel faults if the faults are not within the defined threshold range.
Particularly, an improved G-P algorithm is adopted to solve the correlation dimension, and the main improvement is as follows: euclidean distance r between any two points in space for solving vibration signal reconstructionijIn time, the recursion formula adopted for improving the accuracy and the calculation speed is as follows:
Figure BDA0003382682760000071
Figure BDA0003382682760000072
Figure BDA0003382682760000073
wherein r isijIs Euclidean distance, x (i) is vibration signal time sequence, and m is embedding dimension; τ is the delay time, Xi (m)I-th time series vector of m-dimensional space, Xj (m)A j-th time sequence vector of an m-dimensional space, wherein i and j are the i and j moments respectively;
Figure BDA0003382682760000081
Figure BDA0003382682760000082
Figure BDA0003382682760000083
where C (m, r) is the correlation function, D (m) is the correlation dimension, H (x) is the step function, r is the critical distance, N is the time series length, and x is x (i).
In particular, the vector space coordinate system formed by the maximum Lyapunov exponent, the K entropy and the correlation dimension needs to be arranged in order of corresponding coordinate axes.
In particular, if the maximum Lyapunov exponent, the K entropy and the correlation dimension of the vibration signal in the fault state need to simultaneously satisfy a defined threshold range, the fault is a known type fault, otherwise, the fault is an unknown fault.
In the embodiment, a mechanical fault simulation test of a winding core is performed on a 10kV single-phase oil immersed shunt reactor with the model number of JSRT-ACL 11H. The acquisition instrument adopts a DH5922D acquisition instrument, and the sensor adopts an acceleration sensor with 1A212E type sensitivity of 500mV/g (g is 9.8 m.s-2). The sensors are distributed on the surface of the reactor box in an array mode, and the total number of the sensors is 48, as shown in the attached figure 2. The vibration signal sampling frequency is set to 20kHz in consideration of the frequency range of the reactor vibration signal.
During fault simulation, mechanical faults of the reactor winding iron core are simulated through artificial setting, and the normal state of the reactor winding iron core, the axial looseness 50% state of the winding iron core, the axial looseness 100% state of the winding iron core, the radial looseness 30% state of the winding iron core, the radial looseness 60% state of the winding iron core and the radial looseness 100% state of the winding iron core under rated voltage are respectively carried out, and six states are total. The method comprises the steps of performing core hanging operation on the reactor before setting the pressing force of the winding iron core, then setting the size of the pressing force, recovering the core hanging of the reactor after the setting of the pressing force is completed, and performing vibration signal acquisition after standing for 24 hours.
The measuring point No. 4 on the top surface is selected for analysis, and after the vibration signal is preprocessed (namely, subjected to noise reduction), time domain graphs of the measuring points No. 4 with different fault degrees are shown in FIG. 3. As can be seen from FIG. 3, the time domain waveforms of the vibration signals of the reactor winding iron core under different degrees of axial looseness and radial looseness are different and approximate to sine, and obvious nonlinearity is presented. And then, a correlation integration method is adopted to obtain K entropy values of the vibration signals of the measuring point No. 4 on the top surface under different states. The K entropy calculation results for the top measurement point No. 4 are given in Table 1. As can be seen from Table 1, the K entropy values in the 6 states are all larger than 0, so that the vibration signal of the reactor has chaotic characteristics.
Table 1 top surface 4 measuring point K entropy calculation result
Figure BDA0003382682760000091
Calculating multiple chaotic characteristic indexes of No. 4 measuring points on the top surface: and (3) randomly selecting 120 groups of data in 6 states according to the maximum Lyapunov index, the correlation dimension value and the K entropy value, wherein 20 groups of data in each state are selected for 0.2 second, and respectively calculating multiple chaos characteristic index values of the selected data. The maximum Lyapunov exponent, the K entropy value and the correlation dimension value calculated by 120 groups of data in different states are shown in the attached figure 4.
And respectively taking the maximum Lyapunov index, the K entropy and the correlation dimension as an x axis, a y axis and a z axis to construct a multi-chaos feature identification space, and projecting the calculated multi-chaos index value to the multi-chaos feature identification space, as shown in the attached figure 5. As can be seen from the attached figure 5, in the chaotic characteristic space, the axial looseness and the radial looseness of the reactor winding iron core are effectively separated, the positions of different looseness degrees in the characteristic space are clearly displayed, and the aliasing and crossing phenomena do not occur in clusters in different states. Therefore, the multi-chaotic characteristic space can accurately and effectively identify different fault types and fault degrees of the mechanical fault of the high-resistance winding iron core. It is worth explaining that the chaotic feature space can accurately finish the classification and identification of the mechanical fault of the high-resistance winding iron core without a large number of training samples and deep learning, and is helpful for solving the problem that the intelligent learning algorithm is used for diagnosing the insufficient field fault samples at present.
And according to the positions of different chaotic indexes in the multi-chaotic feature space, defining threshold value ranges corresponding to different indexes in different states. The maximum Lyapunov exponent, the K entropy and the associated dimension range in the normal state are respectively as follows: [0.0018,0.0065], [20.0400,28.9587] and [1.0692,1.0721 ]. The values of the three chaotic indexes can be determined to be in a normal state only if the values of the three chaotic indexes simultaneously meet the threshold value range, and the chaotic indexes are in a fault state if one index value is not in the range. The maximum Lyapunov exponent, K entropy and the associated dimension of 50% axial looseness of the winding core are respectively in the ranges of [0.0008,0.0067], [24.9901,27.0929] and [1.1930,1.2055 ]; the maximum Lyapunov exponent, K entropy and the associated dimension of 100% axial looseness of the winding core are respectively in the ranges of [0.0004,0.0035], [48.354,53.4185] and [1.2277,1.2323 ]; the maximum Lyapunov exponent, K entropy and the associated dimension of 30% radial looseness of the winding core are respectively [0.0010,0.0035], [21.6138,22.2433] and [1.1218,1.1261 ]; the maximum Lyapunov exponent, K entropy and the associated dimension of 60% radial looseness of the winding core are respectively [0.0023,0.0069], [21.5350,22.9634] and [1.1705,1.1738 ]; the maximum Lyapunov exponent, K entropy and associated dimension for 100% radial looseness of the winding core range from [0.0024,0.0076], [34.0047,37.7458] and [1.1350,1.1380], respectively. If the fault range is within the cluster threshold range of the existing fault, the fault range is a known fault, and otherwise, the fault range is an unknown new fault.
Example two:
a chaos feature space-based high-voltage shunt reactor state judgment system can realize a chaos feature space-based high-voltage shunt reactor state judgment method in the first embodiment, and comprises the following steps:
the signal acquisition module: the method comprises the steps of obtaining a vibration signal of the surface of a reactor box body;
a chaotic characteristic judgment module: the chaotic signal generator is used for judging whether the vibration signal has chaotic characteristics or not;
a chaotic characteristic calculation module: the device is used for responding to the fact that the vibration signal has the chaos characteristic, and calculating a multi-chaos characteristic value of the vibration signal;
a feature projection module: the system is used for projecting multiple chaotic characteristic values to multiple chaotic characteristic identification spaces;
a state determination module: the method is used for judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space.
Example three:
the embodiment of the invention also provides a device for judging the state of the high-voltage shunt reactor based on the chaotic characteristic space, which can realize the method for judging the state of the high-voltage shunt reactor based on the chaotic characteristic space in the first embodiment and comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method of:
acquiring a vibration signal on the surface of a reactor box body;
judging whether the vibration signal has chaotic characteristics;
when the vibration signal has the chaos characteristic, calculating a multi-chaos characteristic value of the vibration signal;
projecting the multiple chaotic characteristic values to multiple chaotic characteristic identification spaces;
and judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space.
Example four:
the embodiment of the invention also provides a computer readable storage medium, which can realize the method for judging the state of the high-voltage shunt reactor based on the chaotic feature space in the first embodiment, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the method comprises the following steps:
acquiring a vibration signal on the surface of a reactor box body;
judging whether the vibration signal has chaotic characteristics;
when the vibration signal has the chaos characteristic, calculating a multi-chaos characteristic value of the vibration signal;
projecting the multiple chaotic characteristic values to multiple chaotic characteristic identification spaces;
and judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space.
As will be appreciated by one skilled in the art, 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 flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 processor, 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.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.

Claims (10)

1. The method for judging the state of the high-voltage shunt reactor based on the chaotic feature space is characterized by comprising the following steps of:
acquiring a vibration signal on the surface of a reactor box body;
judging whether the vibration signal has chaotic characteristics;
when the vibration signal has the chaos characteristic, calculating a multi-chaos characteristic value of the vibration signal;
projecting the multiple chaotic characteristic values to multiple chaotic characteristic identification spaces;
and judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space.
2. The method for judging the state of the high-voltage shunt reactor based on the chaotic feature space, as claimed in claim 1, wherein the step of judging whether the vibration signal has the chaotic characteristic comprises the steps of:
calculating a K entropy value of the vibration signal by a correlation integral method;
responding to the fact that the K entropy value is not larger than 0, and the vibration signal does not have the chaotic characteristic;
responding to the fact that the K entropy value is larger than 0, and the vibration signal has a chaotic characteristic;
when the vibration signal has the chaos characteristic, the multi-chaos characteristic value of the vibration signal is calculated, and the method comprises the following steps:
and calculating the correlation dimension of the vibration signal through an improved G-P algorithm, and solving the maximum Lyapunov index of the vibration signal through a small data volume method, wherein the multiple chaos eigenvalues comprise the maximum Lyapunov index, a K entropy value and the correlation dimension.
3. The method for judging the state of the high-voltage shunt reactor based on the chaotic feature space according to claim 2, wherein the improved G-P algorithm comprises a recursion formula, and the recursion formula is as follows:
Figure FDA0003382682750000011
Figure FDA0003382682750000012
Figure FDA0003382682750000021
wherein r isijIs Euclidean distance, x (i) is vibration signal time sequence, and m is embedding dimension; τ is the delay time, Xi (m)I-th time series vector of m-dimensional space, Xj (m)A j-th time sequence vector of an m-dimensional space, wherein i and j are the i and j moments respectively;
Figure FDA0003382682750000022
Figure FDA0003382682750000023
Figure FDA0003382682750000024
where C (m, r) is the correlation function, D (m) is the correlation dimension, H (x) is the step function, r is the critical distance, N is the time series length, and x is x (i).
4. The method for judging the state of the high-voltage shunt reactor based on the chaotic feature space according to claim 2, wherein the maximum Lyapunov index, the K entropy and the correlation dimension in the multi-chaotic feature recognition space are respectively used as an x axis, a y axis and a z axis, and the coordinate axes are arranged in sequence.
5. The method for judging the state of the high-voltage shunt reactor based on the chaotic feature space according to claim 2, wherein the step of judging the state of the reactor corresponding to the multiple chaotic feature values in the multiple chaotic feature recognition space comprises the following steps:
judging whether the multiple chaotic characteristic index values are all in a multiple chaotic characteristic index threshold range corresponding to a certain state in a multiple chaotic characteristic identification space;
when the multi-chaos characteristic index values are all in the range of the multi-chaos characteristic index threshold corresponding to a certain state, determining that the reactor state is the reactor state corresponding to the multi-chaos characteristic index threshold;
and when the multiple chaotic characteristic index values are not in the multiple chaotic characteristic index threshold range corresponding to a certain state, determining that the state of the reactor is a new fault.
6. The method for judging the state of the high-voltage shunt reactor based on the chaotic feature space as claimed in claim 5, wherein the multi-chaotic feature index threshold range is determined by dividing in a feature recognition space after repeatedly calculating chaotic feature values of the vibration signals in the same state at different time periods.
7. The method for judging the state of the high-voltage parallel reactor based on the chaotic feature space of claim 1, wherein the reactor state comprises a normal state of a reactor winding iron core, a 50% axial looseness state of the winding iron core, a 100% axial looseness state of the winding iron core, a 30% radial looseness state of the winding iron core, a 60% radial looseness state of the winding iron core and a 100% radial looseness state of the winding iron core.
8. High-voltage shunt reactor state judgment system based on chaos characteristic space, its characterized in that includes:
the signal acquisition module: the method comprises the steps of obtaining a vibration signal of the surface of a reactor box body;
a chaotic characteristic judgment module: the chaotic signal generator is used for judging whether the vibration signal has chaotic characteristics or not;
a chaotic characteristic calculation module: the device is used for responding to the fact that the vibration signal has the chaos characteristic, and calculating a multi-chaos characteristic value of the vibration signal;
a feature projection module: the system is used for projecting multiple chaotic characteristic values to multiple chaotic characteristic identification spaces;
a state determination module: the method is used for judging the reactor state corresponding to the multiple chaotic characteristic values in the multiple chaotic characteristic identification space.
9. The high-voltage shunt reactor state judgment device based on the chaotic feature space is characterized by comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 7.
10. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
CN202111440545.0A 2021-11-30 2021-11-30 High-voltage parallel reactor state judgment system and method based on chaotic feature space Pending CN114117923A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111440545.0A CN114117923A (en) 2021-11-30 2021-11-30 High-voltage parallel reactor state judgment system and method based on chaotic feature space

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111440545.0A CN114117923A (en) 2021-11-30 2021-11-30 High-voltage parallel reactor state judgment system and method based on chaotic feature space

Publications (1)

Publication Number Publication Date
CN114117923A true CN114117923A (en) 2022-03-01

Family

ID=80368284

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111440545.0A Pending CN114117923A (en) 2021-11-30 2021-11-30 High-voltage parallel reactor state judgment system and method based on chaotic feature space

Country Status (1)

Country Link
CN (1) CN114117923A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114722492A (en) * 2022-03-22 2022-07-08 南京依维柯汽车有限公司 Method for identifying and decomposing chaotic vibration of engine suspension system
CN115420499A (en) * 2022-11-04 2022-12-02 北谷电子有限公司 Gearbox fault diagnosis method and system based on Lyapunov exponent

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114722492A (en) * 2022-03-22 2022-07-08 南京依维柯汽车有限公司 Method for identifying and decomposing chaotic vibration of engine suspension system
CN115420499A (en) * 2022-11-04 2022-12-02 北谷电子有限公司 Gearbox fault diagnosis method and system based on Lyapunov exponent

Similar Documents

Publication Publication Date Title
CN107784325B (en) Spiral fault diagnosis method based on data-driven incremental fusion
Chen et al. A meta-learning method for electric machine bearing fault diagnosis under varying working conditions with limited data
CN106443316B (en) Multi-information detection method and device for deformation state of power transformer winding
CN110110768B (en) Rolling bearing fault diagnosis method based on parallel feature learning and multiple classifiers
CN111191740B (en) Fault diagnosis method for rolling bearing
CN114117923A (en) High-voltage parallel reactor state judgment system and method based on chaotic feature space
CN106841949B (en) Method and device for monitoring stator insulation of three-phase asynchronous alternating current motor on line
CN112098088B (en) Rolling bearing fault diagnosis method based on KICA-fractal theory
CN111881594B (en) Non-stationary signal state monitoring method and system for nuclear power equipment
CN114091504A (en) Rotary machine small sample fault diagnosis method based on generation countermeasure network
CN116956215A (en) Fault diagnosis method and system for transmission system
CN117628005A (en) Signal-fused hydraulic motor fault diagnosis method and system
CN113076354A (en) User electricity consumption data analysis method and device based on non-invasive load monitoring
Zhu et al. Aiming to Complex Power Quality Disturbances: A Novel Decomposition and Detection Framework
Wu et al. A fault diagnosis method of rotating machinery based on multi-scale fuzzy entropy
CN115236272A (en) Gas sensor fault diagnosis method and device under multi-working condition and storage medium
CN115291156A (en) Online detection system and detection method for error characteristics of voltage transformer
He et al. Application and comparative analysis of traditional machine learning and deep learning in transmission line fault classification
CN116451105A (en) Wind turbine generator system gearbox fault diagnosis method based on ICEEMDAN-MPE-RF and SVM
Zhang et al. Diagnosis methods for inter-turn short-circuit fault degree of permanent magnet synchronous motor stator winding
Xing et al. A method of classified HV circuit breaker fault signal based on EEMD and SOM neural network
Wu et al. Recognition method of voltage sag sources based on RMT-CNN model
Yu et al. Application of distance measure in KNN motor fault diagnosis
CN114279704B (en) Method and system for monitoring planet-level running state of wind power gear box
Cao et al. Research on automatic fault diagnosis based on time-frequency characteristics and PCA-SVM

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