CN117371207A - Extra-high voltage converter valve state evaluation method, medium and system - Google Patents
Extra-high voltage converter valve state evaluation method, medium and system Download PDFInfo
- Publication number
- CN117371207A CN117371207A CN202311315943.9A CN202311315943A CN117371207A CN 117371207 A CN117371207 A CN 117371207A CN 202311315943 A CN202311315943 A CN 202311315943A CN 117371207 A CN117371207 A CN 117371207A
- Authority
- CN
- China
- Prior art keywords
- converter valve
- state
- evaluation
- membership
- index
- 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
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 161
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 37
- 238000004088 simulation Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 description 16
- 238000005070 sampling Methods 0.000 description 8
- 230000005236 sound signal Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000002986 genetic algorithm method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004091 panning Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/60—Arrangements for transfer of electric power between AC networks or generators via a high voltage DC link [HVCD]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides an extra-high voltage converter valve state evaluation method, medium and system, which belong to the technical field of extra-high voltage converter valve state evaluation, and comprise the following steps: acquiring operation parameters of a converter valve and preprocessing; according to the structural characteristics of the converter valve, establishing a layered and graded converter valve state evaluation index system; calculating the weight of each level evaluation index in the evaluation index system; calculating index data of each level in the evaluation index system according to the operation parameters; establishing a membership function of each evaluation index based on a fuzzy theory; calculating the membership degree of each level evaluation index according to the pretreatment index data by using a membership degree function; and carrying out hierarchical fuzzy comprehensive evaluation on the obtained membership degree, and visually outputting membership probabilities of a normal state, an attention state, an abnormal state and a serious state of the converter valve and a component thereof. The method and the device can solve the technical problem of inaccurate evaluation of the extra-high voltage converter valve state in the prior art.
Description
Technical Field
The invention belongs to the technical field of extra-high voltage converter valve state evaluation, and particularly relates to an extra-high voltage converter valve state evaluation method, medium and system.
Background
With the continuous increase of the demands of the power system for high reliability and high efficiency and energy conservation, higher demands are also put forward on the state monitoring and fault diagnosis technology of key power equipment. The extra-high voltage converter valve is used as core equipment of extra-high voltage direct current transmission engineering, and the running state of the extra-high voltage converter valve is a key point for the safety and stability of a direct current system. Under the background of ultra-high voltage and high-duty ratio new energy, the artificial intelligence technology is applied to the power system, can fully utilize power grid resources, saves operation and maintenance management cost, and has wide application prospect. The intelligent power grid is intelligently extended and developed from system intellectualization to equipment intellectualization, and unification and standardization of an information system, a monitoring system, an evaluation system and a management system of the power equipment are realized. The extra-high voltage converter valve is one of key equipment in an extra-high voltage direct current transmission system, and the running state of the extra-high voltage converter valve directly influences the safe and stable running of the whole direct current transmission system. The traditional state monitoring and fault diagnosis method of the converter valve has a plurality of defects, so that the accurate early warning and the position diagnosis of the fault of the converter valve cannot be realized, and the development of an advanced state evaluation method of the converter valve is urgently needed.
At present, the state evaluation method of the converter valve mainly comprises a fault tree-based analysis method, an expert system method, a fuzzy evaluation method and the like. The fault tree analysis method is used for analyzing the logic relation among fault events by constructing a fault tree model of the converter valve, determining the root cause and occurrence probability of the fault of the converter valve and realizing early warning of the fault. However, this method relies on expert experience and has a certain subjectivity. The expert system method utilizes a knowledge base and an reasoning mechanism to simulate an expert to perform fault analysis, but the construction of a rule base of the expert system method also depends on expert experience. The fuzzy evaluation method uses membership function and fuzzy reasoning to qualitatively describe the state of the converter valve, so as to evaluate the health state of the equipment, but quantitative analysis of the evaluation result is insufficient. In general, the existing evaluation method has the problems of inaccurate evaluation and the like.
Disclosure of Invention
In view of the above, the invention provides a method, medium and system for evaluating the state of an extra-high voltage converter valve, which can solve the technical problem of inaccurate evaluation of the state of the extra-high voltage converter valve in the prior art.
The invention is realized in the following way:
the first aspect of the invention provides an extra-high voltage converter valve state evaluation method, which comprises the following steps:
s10, acquiring operation parameters of a converter valve and preprocessing, wherein the operation parameters comprise voltage, current, sound and images;
s20, establishing a layered and graded converter valve state evaluation index system according to the structural characteristics of the converter valve, wherein the evaluation index system comprises a plurality of evaluation indexes;
s30, calculating the weight of each level evaluation index in the evaluation index system;
s40, calculating index data of each level in the evaluation index system according to the operation parameters;
s50, establishing membership functions of all evaluation indexes based on a fuzzy theory;
s60, calculating the membership degree of each level evaluation index according to the pretreatment index data by using a membership degree function;
and S70, performing hierarchical fuzzy comprehensive evaluation on the obtained membership degree, and visually outputting membership probabilities of a normal state, an attention state, an abnormal state and a serious state of the converter valve and a component thereof.
Preferably, the voltage and current preprocessing method in the operation parameters is multi-physical field model simulation check.
Based on the technical scheme, the state evaluation method of the extra-high voltage converter valve can be improved as follows:
the step of obtaining the operation parameters of the converter valve and preprocessing specifically comprises the following steps:
acquiring original signals of a converter valve, including voltage, current, sound and image signals, acquired by a sensor or a video terminal;
preprocessing the original signal, including filtering and denoising;
and extracting effective characteristics from the preprocessed signals as operation parameters of state evaluation.
The beneficial effects of adopting above-mentioned improvement scheme are: the accuracy and reliability of state estimation can be improved by preprocessing and feature extraction.
The evaluation index system is divided into a converter valve overall level, an internal component level and a specific device level according to the structural characteristics of the converter valve.
The method for calculating the weight of each level evaluation index in the evaluation index system is a level single-order method.
The step of calculating the index data of each level in the evaluation index system according to the operation parameters further comprises the step of performing fuzzy calculation on the index data of each level to obtain an index quantized value.
The step of establishing the membership function of each evaluation index based on the fuzzy theory specifically comprises the following steps:
determining a language variable, judging according to the state of the converter valve, and selecting the language variable describing the state;
establishing a membership function, determining membership functions corresponding to different language values aiming at each evaluation index, and describing membership relations between index values and the language values;
standardized conversion, performing standardized treatment on each evaluation index, and mapping the standardized treatment to a [0,1] interval;
and constructing a membership matrix, and calculating the membership of each language value corresponding to the index data according to the membership function of each evaluation index to form the membership matrix.
The step of performing hierarchical fuzzy comprehensive evaluation on the obtained membership degree specifically comprises the following steps:
dividing the state of the converter valve into 4 grades which are normal, noticeable, abnormal and serious;
calculating membership according to the hierarchical relationship of the index system;
and finding out a corresponding maximum state grade according to the obtained membership degree to be used as a grading fuzzy comprehensive evaluation result.
Further, the membership probability is the membership degree corresponding to the grading fuzzy comprehensive evaluation result.
A third aspect of the present invention provides a computer readable storage medium, where the computer readable storage medium stores program instructions, and the program instructions are used to execute the above-mentioned extra-high voltage converter valve state evaluation method when the program instructions are executed.
The invention provides an extra-high voltage converter valve state evaluation system, which comprises the computer readable storage medium.
Compared with the prior art, the method, the medium and the system for evaluating the state of the extra-high voltage converter valve have the beneficial effects that:
1. comprehensive system of evaluation index system
The invention constructs a layered and graded converter valve state evaluation index system which comprehensively considers various factors influencing the running state of the converter valve from three layers of the whole converter valve, the internal components and the specific devices. And a plurality of evaluation indexes are arranged under each level, and the evaluation index system is comprehensive in system and can be used for three-dimensionally evaluating the state of the converter valve.
2. Quantitative and accurate evaluation result
According to the invention, various operation parameters are collected, index membership is calculated, and then fuzzy comprehensive evaluation is carried out, so that quantitative description of the state of the converter valve is realized. Compared with qualitative evaluation, the quantitative evaluation result is more accurate and reliable, different fault states can be clearly and quantitatively distinguished, and a foundation is provided for subsequent fault early warning and fault positioning.
3. Fault early warning and positioning accuracy
Based on the quantitative evaluation result of the invention, the health state probabilities of the whole converter valve and different components, such as membership of normal, attention, abnormal and serious fault states, can be intuitively output. This provides support for accurate early warning of faults. And by comparing the evaluation results of the indexes of different levels, the source component causing the fault can be judged, so that the accuracy of fault positioning is improved.
4. The method has strong practicability
The invention realizes state evaluation by using a fuzzy theory method, and is highly matched with the actual operation height of the converter valve. The index weight can be adjusted according to actual needs, and the method is high in practicability. And the evaluation result can be visually displayed, so that on-site operators can conveniently and rapidly judge the state of the equipment.
In conclusion, the method solves the technical problem of inaccurate evaluation of the extra-high voltage converter valve state in the prior art.
Drawings
FIG. 1 is a flow chart of an extra-high voltage converter valve state evaluation method provided by the invention;
FIG. 2 is a schematic diagram of simulation verification of multiple physical field models in operating parameters according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a hierarchical evaluation index system according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, a flowchart of a first embodiment of an extra-high voltage converter valve state evaluation method according to a first aspect of the present invention is provided, where the method in this embodiment includes the following steps:
s10, acquiring and preprocessing operation parameters of a converter valve, wherein the operation parameters comprise voltage, current, sound and images;
s20, establishing a layered and graded converter valve state evaluation index system according to the structural characteristics of the converter valve, wherein the evaluation index system comprises a plurality of evaluation indexes;
s30, calculating the weight of each level evaluation index in the evaluation index system;
s40, calculating index data of each level in the evaluation index system according to the operation parameters;
s50, establishing membership functions of all evaluation indexes based on a fuzzy theory;
s60, calculating the membership degree of each level evaluation index according to the pretreatment index data by using a membership degree function;
and S70, performing hierarchical fuzzy comprehensive evaluation on the obtained membership degree, and visually outputting membership probabilities of a normal state, an attention state, an abnormal state and a serious state of the converter valve and a component thereof.
In the above technical solution, the steps of obtaining the operation parameters of the converter valve and performing pretreatment specifically include:
acquiring original signals of a converter valve, including voltage, current, sound and image signals, acquired by a sensor or a video terminal;
preprocessing the original signal, including filtering and denoising;
and extracting effective characteristics from the preprocessed signals as operation parameters of state evaluation.
The voltage and current preprocessing method in the operation parameters is multi-physical field model simulation check.
The voltage and current preprocessing method in the operation parameters is multi-physical field model simulation check, and can be realized by adopting the following method: the electric quantity and multi-physical quantity panoramic data of the converter valve equipment are collected by means of an existing converter valve control system, an existing converter valve water cooling system and external temperature and pressure sensors, a two-way multi-physical-field simulation model is built, a circuit simulation model is built on the basis of simulink, a thermal field and pressure field simulation model is built on the basis of Ansys, and the circuit model is built on the basis of electric quantity such as monitored voltage and current, and the thermal field and pressure field model is mainly based on temperature and pressure data acquired by the multi-physical sensors. The two simulation models are mutually checked, the thermal field and the pressure field of the converter valve under different working conditions are converted into updated circuit parameters through interactive programs, the electrical quantity of the circuit simulation reflects aging loss, the thermal field and the pressure field are updated through the updated loss, the two simulation models are mutually checked, and finally, an accurate converter valve multi-physical field model reflecting actual working conditions is obtained, and an accurate data source is provided for a later established index system.
In the technical scheme, the evaluation index system is divided into a whole level, an internal component level and a specific device level of the converter valve according to the structural characteristics of the converter valve.
In the above technical solution, the method for calculating the weight of each level of evaluation index in the evaluation index system is a level single ranking method.
In the above technical solution, the step of calculating the index data of each level in the evaluation index system according to the operation parameter further includes a step of performing fuzzy calculation on the index data of each level to obtain an index quantized value.
In the above technical solution, the step of establishing a membership function of each evaluation index based on the fuzzy theory specifically includes:
determining a language variable, judging according to the state of the converter valve, and selecting the language variable describing the state;
establishing a membership function, determining membership functions corresponding to different language values aiming at each evaluation index, and describing membership relations between index values and the language values;
standardized conversion, performing standardized treatment on each evaluation index, and mapping the standardized treatment to a [0,1] interval;
and constructing a membership matrix, and calculating the membership of each language value corresponding to the index data according to the membership function of each evaluation index to form the membership matrix.
In the above technical solution, the step of performing hierarchical fuzzy comprehensive evaluation on the obtained membership degree specifically includes:
dividing the state of the converter valve into 4 grades which are normal, noticeable, abnormal and serious;
calculating membership according to the hierarchical relationship of the index system;
and finding out a corresponding maximum state grade according to the obtained membership degree to be used as a grading fuzzy comprehensive evaluation result.
Further, in the above technical solution, the membership probability is a membership degree corresponding to the hierarchical fuzzy comprehensive evaluation result.
The specific embodiment of step S10 is described as follows:
data acquisition
The step first requires acquisition of the operating parameters of the converter valve, including voltage, current, sound and image.
1.1 Voltage Signal acquisition
And measuring a voltage signal U (t) of the converter valve terminal in real time by using a voltage sensor, wherein the sampling frequency is 1000Hz.
1.2 Current Signal acquisition
The current signal I (t) of the converter valve terminal is measured in real time by using a current sensor, and the sampling frequency is also selected to be 1000Hz.
1.3 Sound Signal acquisition
The acoustic signal S (t) generated during operation of the converter valve is measured in real time using a dedicated acoustic sensor. The sampling frequency was chosen to be 44100Hz taking into account the frequency characteristics of the sound signal.
1.4 image Signal acquisition
And acquiring an image of the running state of the converter valve by using a video terminal, and acquiring an image sequence P (x, y, t), wherein P (x, y, t) represents the pixel value of the original image at a coordinate point (x, y). Considering the spatial resolution of the image, the acquisition frame rate of the video terminal is chosen to be 50fps, and the resolution is 1280×720.
Signal preprocessing
The acquired original signal may have noise interference, and the direct use of the original signal in state evaluation is easy to introduce errors. Therefore, necessary pretreatment is required.
2.1 Voltage Signal pretreatment
The obtained voltage signal U (t) is subjected to the following preprocessing:
(1) Median filtering is carried out to remove scattered noise;
u' (T) =med { U (T-T),..u (T),., U (t+t) }; t represents sampling time and sampling time represented by T;
(2) Wavelet transform denoising
A low-pass filter is designed based on wavelet transformation to filter out high-frequency noise. Let the wavelet transform be W (U') (a, b), the filtering process is:
U″(t)=IW s (U′)(a,b)
wherein I represents wavelet inverse transformation, W s Representing wavelet transforms, a, b representing scale and panning parameters.
2.2 Current Signal pretreatment
The same preprocessing method as the voltage signal is used for the current signal I (t).
Median filtering:
I′(t)=med{I(t-T),...,I(t),...,I(t+T)};
wavelet transformation filtering:
I″(t)=IW s (I′)(a,b);
2.3 Sound Signal pretreatment
For sound signal S (t):
(1) Band-pass filtering, reserving a main sound frequency band [100,1000] Hz;
(2) Self-adaptive noise reduction, namely self-adaptive noise filtering by using an NLMS algorithm;
e(n)=d(n)-y(n);
y(n)=W T (n)X(n);
where d (n) is the input signal, y (n) is the filtered output signal, W (n) is the filter weight, X (n) is the block of the input signal, e (n) is the error, μ and δ are the algorithm adjustment parameters, typically μ=1, δ=0, μ and δ can be adjusted in actual use according to the noise reduction effect, n is the number of sampling points of the sound signal, typically 1.
2.4 image Signal preprocessing
Preprocessing the image sequence P (x, y, t):
(1) Median filtering and denoising;
p' (x, y, t) =med { P (x-M, y-M, t),., P (x, y, t),., P (x+m, y+m, t) }; m represents half the size of the filtering template, and x and y are the abscissas of the image.
(2) Motion compensation, estimating a motion vector field MV (x, y, t) using a light flow algorithm, performing motion compensation:
P″(x,y,t)=P′(x+MV x ,y+MV y ,t);
wherein MV (x, y, t) represents a motion vector of a position (x, y) at a time t and is estimated by an optical flow algorithm; MV (motion vector) x An x component representing a motion vector; MV (motion vector) y A y component representing a motion vector;
parameter extraction
And extracting characteristic parameters required by state evaluation from the preprocessed signals.
3.1 Electrical parameter extraction
Effective values, frequency analysis features are extracted from U '(t) and I' (t).
Voltage effective value:
current effective value:
voltage spectrum characteristics:
P U (f)=|FFT(U″(t))|;
current spectral characteristics:
P I (f)=|FFT(I″(t))|;
3.2 Acoustic parameter extraction
Features such as sound power, mel Frequency Cepstrum Coefficient (MFCC) are extracted from the sound signal S "(t). Sound power:
MFCC characteristics:
MFCC=DCT(log(Mel(S″(t))));
where Mel is the Mel filter bank and DCT is the discrete cosine transform.
3.3 image parameter extraction
From the image sequence P "(x, y, t), features such as motion and texture can be extracted.
Image motion characteristics:
in the method, in the process of the invention,representing normalizing the summation result to obtain average motion amplitude;
image texture features:
F(t)=GLCM(P″(x,y,t));
wherein GLCM is a gray level co-occurrence matrix algorithm.
Preprocessing and feature extraction can improve the accuracy and reliability of state assessment.
The specific implementation manner of step S20 is as follows:
index architecture
According to the structural characteristics of the converter valve, selecting an evaluation index and establishing a hierarchical evaluation index system, as shown in fig. 3:
integral level of converter valve
Insulation indexes include air gap insulation, coil insulation and the like;
the temperature rise index comprises the heating level of a converter valve;
airtight index, including airtight performance of specific device;
the internal component hierarchy includes:
the main contact index is used for monitoring the contact state of the main contact;
an auxiliary contact index, namely monitoring the contact state of an auxiliary contact;
the control switch index is that the state of the control switch is monitored;
the filter index is the filtering effect of the filter;
the specific device hierarchy is specific to the specific devices that make up each component;
the index weight comprises:
according to the severity of the influence on the state of the equipment, the index is given a weight:
the overall level weight of the converter valve is 0.4;
the internal component hierarchy weight is 0.3;
the specific device level weight is 0.3;
the mathematical model establishment comprises the following steps: the weights of the individual indicators are determined using analytic hierarchy process.
(1) Constructing a judgment matrix
Comparing the importance of every two indexes, and establishing a judgment matrix A= [ a ] ij ];
Wherein a is ij The importance comparison result of the index i and the index j is shown.
(2) Hierarchical single ordering
Calculating a eigenvector W of the matrix A:
A W =λ max W;
w is the weight vector of each index.
(3) Consistency check
Calculating a consistency index:
m represents the number of indices.
RI is the average random uniformity index whenWhen the matrix passes the consistency check, CR represents the proportion of the consistency index.
The fuzzy comprehensive judgment comprises the following steps: and (5) performing quantitative conversion of qualitative indexes by adopting a fuzzy comprehensive evaluation method of fuzzy mathematics.
1 defining a language evaluation set of indexes, wherein V= { is excellent, good, slightly good, general, poor, very poor and very poor };
2, constructing a membership function of the language evaluation.
Determining membership functions
For each evaluation index, determining membership functions of different language values:
taking a converter valve temperature rise index as an example:
and so on to establish other membership functions.
3, performing fuzzy calculation:
wherein A is ij The j-th language evaluation being the i-th index, R ij Is the corresponding membership degree, B i Is the result of the comprehensive evaluation, R in this step ij Is an unknown quantity.
4 pairs B i Maximizing membership degree to obtain quantitative index and R ij Specific values of (3).
Through the step, a scientific and reasonable converter valve state evaluation index system can be obtained.
In step S30, the weights of the evaluation indexes of each level in the evaluation index system are established and iterated by adopting a genetic algorithm method, an optimized objective function is set as a CR value of the hierarchical sequence, and an optimal weight is obtained when the CR is minimum:
step 1, initializing weight groups
Randomly generating N weight vectors as an initial population W 1 ,W 2 ,...,W N
Each weight vector contains weights of all M evaluation indexes, W i =(w i 1,w i 2,...,w i M),i=1,2,...,N;
The weight initialization range is [0,1], and normalization processing is carried out.
Step 2, evaluating fitness=cr;
for each weight vector W i Constructing a judgment matrix and calculating a CR value;
CR is taken as the FITNESS value of the weight vector and is marked as FINESS (W i )=CR(W i )
Step 3, selecting, crossing and mutating;
selecting a better solution according to the fitness probability, and reserving the solution until the next generation;
performing cross operation on the selected weight vectors to generate new weight vectors;
then, carrying out mutation operation to enhance the diversity of the population;
selecting, crossing and mutating to obtain a new weight group;
step 4, obtaining new weight groups
Taking the selected, crossed and mutated new weight vector as a new generation group;
the new population contains more optimal weight vectors;
step 5, repeating the steps 2-4 until reaching the termination condition;
evaluating the FINESS of the new group, and finding out the optimal weight;
the optimization iteration is repeated until the termination condition is satisfied:
reaching the set maximum iteration times;
the colony FINESS converges, and the continuous generations are similar;
better weight vectors, namely more scientific and reasonable evaluation index weights, can be effectively searched through a genetic algorithm.
Through step S30, each index weight in the state evaluation model can be objectively and reasonably determined.
The specific embodiment of the specific step S40 is described as follows:
electrical parameter calculation
In step S10, the voltage signal U (t) and the current signal I (t) of the converter valve are obtained and preprocessed. The electrical parameter index is calculated at present:
voltage effective value:
where T is the sampling time length.
Current effective value:
voltage harmonic content:
performing fast Fourier transform to obtain a voltage spectrum X (f):
X(f)=FFT(U(t))
calculating harmonic content:
f 1 and f 2 Representing the harmonic frequency range.
Current harmonic content:
the FFT is performed as well, and the current harmonic content IHD is calculated.
Sound parameter calculation
In S10, a sound signal S (t) is obtained, and sound parameters are calculated:
sound power:
sound entropy:
wherein p is i Is the probability distribution of each sampling point of the sound signal.
Acoustic features:
performing FFT (fast Fourier transform) and calculating an acoustic characteristic spectrum:
F(f)=FFT(S(t))
the image parameters use the image motion feature M (t) and the image texture feature F (t) in S10;
fuzzy calculation
And (3) carrying out fuzzy calculation by using a MATLAB fuzzy tool according to the mapping relation between the index system and the parameters to obtain fuzzy quantized values of all the evaluation indexes.
Through step S40, characteristic parameter information required for evaluating the state can be extracted from the signal.
The specific embodiment of step S50 is described as follows:
determining linguistic variables
According to the severity of the state of the converter valve, determining a language variable set:
v= { excellent, good, generally poor, very bad }
Determining membership functions
For each evaluation index, determining membership functions of different language values:
taking a converter valve temperature rise index as an example:
and so on to establish other membership functions.
3. Standardized conversion
Because the dimensions of the evaluation indexes are different, standardized processing is needed:
the index value is mapped to the [0,1] interval.
4. Fuzzy matrix
Building a membership matrix R:
through step S50, fuzzy mapping from index data to language words is realized, and preparation is made for subsequent fuzzy comprehensive evaluation.
The specific embodiment of step S60 is described as follows: and substituting the acquired index data into a membership function of each level evaluation index to calculate and obtain the membership of each level evaluation index.
The specific embodiment of step S70 is described as follows:
clustering classification
And clustering the membership degrees of the level evaluation indexes obtained in the step S60 by using a mean value clustering algorithm to obtain the membership degrees of each state of the converter valve, wherein the membership degrees are represented by { excellent, good, general, poor and extremely poor } and are used for judging that the converter valve is in the state.
Visual presentation: and visually displaying the membership degree of each state in the form of probability diagrams and the like.
Through step S70, accurate evaluation and visual display of the operating state of the converter valve are achieved.
The following is a second embodiment of the method of the present invention, in which specific constants and variables are redefined, unlike the specific constants and variable definitions used in the first embodiment:
step 1, firstly establishing an evaluation index system of a layered hierarchical converter valve
And constructing a three-layer evaluation index system of the bottom-up converter valve by means of device evaluation, component evaluation and converter valve evaluation. Specifically: the method comprises the steps of establishing evaluation index parameter quantities aiming at the converter valve and different groups of components, and dividing the evaluation index parameter quantities into two different grades according to the importance degree of the index parameter quantities, namely a general degree and an importance degree. The index parameters are divided into general state index parameters and important index parameters. Different weights are given for different levels. The evaluation index parameter calculation formula is shown in formula (1).
Z=α*X+β*Y (1)
Wherein Z represents an evaluation result value, X is a general state index parameter evaluation value sum, Y is an important index parameter evaluation value sum, alpha represents a general state index parameter weight, beta represents an important index parameter weight, and the alpha and beta weights are respectively selected to be 0.2 and 0.8.
The method is characterized in that the method is divided into four different grades according to the approach degree of the index parameter value and the normal value range, wherein the four conditions of the index parameter value being in the normal value range, approaching the normal value boundary, exceeding the normal value boundary and seriously exceeding the normal value boundary are divided, and different scores are given for the different grades. The range of normal values is 1, the boundary of the approximate normal value is 5, the boundary of the exceeding normal value is 8, and the boundary of the serious exceeding normal value is 10.
In order to uniformly calculate the evaluation index results of the converter valve and different groups of components, the invention considers that the average value of the sum of the general state index parameter and the important state index parameter value is respectively taken as the comprehensive evaluation value, the comprehensive evaluation value is converted into the percentile, and the calculation formulas are respectively shown as the following (2) and (3).
Wherein x is i Is the i-th general state index parameter evaluation value, y i The evaluation value of the i-th important state index parameter is obtained, and n is the number of the state index parameters.
Step 2, evaluation and classification method based on fuzzy theory
The evaluation results of the converter valve and its group members are classified into four stages, which are a normal state, an attention state, an abnormal state, and a serious state, respectively. The evaluation result states are defined as follows.
(1) The normal state is defined as that the state index parameter values of the converter valve and each group of components are in a normal range, and the equipment operates normally.
(2) Note that the state definition mainly includes two cases, one case in which a single state index parameter value changes, an important state index parameter value approaches a normal range boundary or a single general state index parameter value exceeds a normal range boundary, and the device operates normally without abnormality, and the other case in which a plurality of state index parameter values change, and a plurality of general state index parameter value change trends approach a normal range value boundary, but do not exceed a boundary value, and the device operates normally without abnormality.
(3) An abnormal state is defined as a single significant state index parameter value that varies beyond the normal range boundary, or a plurality of state parameter values that vary beyond the normal range boundary.
(4) A severity condition is defined as a single significant state indicator parameter severely exceeding a normal range boundary, or a plurality of state parameter values exceeding a normal range boundary.
Four equipment state membership functions are constructed according to the evaluation result, and the membership functions of the normal state are shown in a formula (4):
wherein x represents an evaluation result value input by a membership function, and y is a probability value belonging to a normal state.
The membership function of the noted states is shown in equation (5):
wherein x represents the evaluation result value input by the membership function, and y is the probability value of membership to the attention state.
The membership function of the abnormal state is shown in formula (6):
wherein x represents an evaluation result value input by a membership function, and y is a probability value belonging to an abnormal state.
The membership function for the severe state is shown in formula (7):
wherein x represents an evaluation result value input by a membership function, and y is a probability value belonging to a serious state.
According to the evaluation index system and the evaluation method, an evaluation result value is obtained, and the evaluation result value is input into formulas (4), (5), (6) and (7), so that the probability that the equipment state is subordinate to different states can be obtained. For example, the probability values of 43, 47 and 52, which are subordinate to the normal state, the attention state, the abnormal state and the serious state, are (0,0.7,0.3,0), (0,0.3,0.7,0), (0, 1 and 0), respectively, and the probability value of 43 is known to be the attention state, but the probability of 0.3 is the probability of the abnormal state, the probability of 47 is the abnormal state, the attention state is gradually reduced, the probability value of 52 is the abnormal state, and the evaluation classification method for the converter valve based on the fuzzy theory is more suitable for engineering application.
In the above embodiment, the voltage and current preprocessing method in the operating parameters is multi-physical field model simulation check, and may be implemented by the following method with reference to fig. 2: the electric quantity and multi-physical quantity panoramic data of the converter valve equipment are collected by means of an existing converter valve control system, an existing converter valve water cooling system and external temperature and pressure sensors, a two-way multi-physical-field simulation model is built, a circuit simulation model is built on the basis of simulink, a thermal field and pressure field simulation model is built on the basis of Ansys, and the circuit model is built on the basis of electric quantity such as monitored voltage and current, and the thermal field and pressure field model is mainly based on temperature and pressure data acquired by the multi-physical sensors. The two simulation models are mutually checked, the thermal field and the pressure field of the converter valve under different working conditions are converted into updated circuit parameters through interactive programs, the electrical quantity of the circuit simulation reflects aging loss, the thermal field and the pressure field are updated through the updated loss, the two simulation models are mutually checked, and finally, an accurate converter valve multi-physical field model reflecting actual working conditions is obtained, and an accurate data source is provided for a later established index system.
A third aspect of the present invention provides a computer readable storage medium, where the computer readable storage medium stores program instructions, and the program instructions are used to execute the above-mentioned extra-high voltage converter valve state evaluation method when the program instructions are executed.
The invention provides an extra-high voltage converter valve state evaluation system, which comprises the computer readable storage medium.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The method for evaluating the state of the extra-high voltage converter valve is characterized by comprising the following steps of:
s10, acquiring operation parameters of a converter valve and preprocessing, wherein the operation parameters comprise voltage, current, sound and images;
s20, establishing a layered and graded converter valve state evaluation index system according to the structural characteristics of the converter valve, wherein the evaluation index system comprises a plurality of evaluation indexes;
s30, calculating the weight of each level evaluation index in the evaluation index system;
s40, calculating index data of each level in the evaluation index system according to the operation parameters;
s50, establishing membership functions of all evaluation indexes based on a fuzzy theory;
s60, calculating the membership degree of each level evaluation index according to the pretreatment index data by using a membership degree function;
and S70, performing hierarchical fuzzy comprehensive evaluation on the obtained membership degree, and visually outputting membership probabilities of a normal state, an attention state, an abnormal state and a serious state of the converter valve and a component thereof.
2. The method for evaluating the state of an extra-high voltage converter valve according to claim 1, wherein the voltage and current preprocessing method in the operation parameters is multi-physical field model simulation check.
3. The method for evaluating the state of an extra-high voltage converter valve according to claim 1, wherein the step of obtaining the operation parameters of the converter valve and performing the preprocessing specifically comprises:
acquiring original signals of a converter valve, including voltage, current, sound and image signals, acquired by a sensor or a video terminal;
preprocessing the original signal, including filtering and denoising;
and extracting effective characteristics from the preprocessed signals as operation parameters of state evaluation.
4. The ultra-high voltage converter valve state evaluation method according to claim 1, wherein the evaluation index system is divided into a converter valve overall level, an internal component level and a specific device level according to the structural characteristics of the converter valve.
5. The method for evaluating the state of an extra-high voltage converter valve according to claim 1, wherein the method for calculating the weight of each level of evaluation index in the evaluation index system is a level single-order method.
6. The method for evaluating the state of an extra-high voltage converter valve according to claim 1, wherein the step of calculating the index data of each level in the evaluation index system according to the operation parameters further comprises the step of performing fuzzy calculation on the index data of each level to obtain an index quantized value.
7. The method for evaluating the state of an extra-high voltage converter valve according to claim 1, wherein the step of establishing a membership function of each evaluation index based on a fuzzy theory specifically comprises:
determining a language variable, judging according to the state of the converter valve, and selecting the language variable describing the state;
establishing a membership function, determining membership functions corresponding to different language values aiming at each evaluation index, and describing membership relations between index values and the language values;
standardized conversion, performing standardized treatment on each evaluation index, and mapping the standardized treatment to a [0,1] interval;
and constructing a membership matrix, and calculating the membership of each language value corresponding to the index data according to the membership function of each evaluation index to form the membership matrix.
8. The method for evaluating the state of an extra-high voltage converter valve according to claim 1, wherein the step of performing hierarchical fuzzy comprehensive evaluation on the obtained membership degree specifically comprises the following steps:
dividing the state of the converter valve into 4 grades which are normal, noticeable, abnormal and serious;
calculating membership according to the hierarchical relationship of the index system;
and finding out a corresponding maximum state grade according to the obtained membership grade, and taking the maximum state grade as a grading fuzzy comprehensive evaluation result, wherein the membership probability is the membership grade corresponding to the grading fuzzy comprehensive evaluation result.
9. A computer readable storage medium, wherein program instructions are stored in the computer readable storage medium, and the program instructions are used for executing the extra-high voltage converter valve state evaluation method according to any one of claims 1 to 8 when running.
10. An extra-high voltage converter valve condition evaluation system comprising the computer readable storage medium of claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311315943.9A CN117371207A (en) | 2023-10-11 | 2023-10-11 | Extra-high voltage converter valve state evaluation method, medium and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311315943.9A CN117371207A (en) | 2023-10-11 | 2023-10-11 | Extra-high voltage converter valve state evaluation method, medium and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117371207A true CN117371207A (en) | 2024-01-09 |
Family
ID=89392242
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311315943.9A Pending CN117371207A (en) | 2023-10-11 | 2023-10-11 | Extra-high voltage converter valve state evaluation method, medium and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117371207A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117808024A (en) * | 2024-02-29 | 2024-04-02 | 深圳市捷通科技有限公司 | Reader-writer equipment management method and system based on self-adaptive regulation and control |
CN117911011B (en) * | 2024-03-19 | 2024-05-28 | 天津大学 | AC/DC series-parallel power line fault maintenance early warning method |
-
2023
- 2023-10-11 CN CN202311315943.9A patent/CN117371207A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117808024A (en) * | 2024-02-29 | 2024-04-02 | 深圳市捷通科技有限公司 | Reader-writer equipment management method and system based on self-adaptive regulation and control |
CN117808024B (en) * | 2024-02-29 | 2024-05-07 | 深圳市捷通科技有限公司 | Reader-writer equipment management method and system based on self-adaptive regulation and control |
CN117911011B (en) * | 2024-03-19 | 2024-05-28 | 天津大学 | AC/DC series-parallel power line fault maintenance early warning method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111638028B (en) | High-voltage parallel reactor mechanical state evaluation method based on vibration characteristics | |
CN109164343B (en) | Transformer fault diagnosis method based on characteristic information quantization and weighted KNN | |
Li et al. | Feature extraction for rolling element bearing fault diagnosis utilizing generalized S transform and two-dimensional non-negative matrix factorization | |
CN117371207A (en) | Extra-high voltage converter valve state evaluation method, medium and system | |
CN112036042B (en) | Power equipment abnormality detection method and system based on variational modal decomposition | |
CN110929918A (en) | 10kV feeder line fault prediction method based on CNN and LightGBM | |
CN106504122B (en) | Fault monitoring method and system of ring main unit based on neighborhood preserving embedding algorithm | |
JP2000512766A (en) | Statistical pattern analysis method for partial discharge measurement in high voltage insulation | |
CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
CN111209934A (en) | Fan fault prediction and alarm method and system | |
CN111273125A (en) | RST-CNN-based power cable channel fault diagnosis method | |
CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
CN115587309A (en) | Method, device and equipment for extracting key features of short-circuit resistance of transformer | |
CN113036913A (en) | Method and device for monitoring state of comprehensive energy equipment | |
CN113470694A (en) | Remote listening monitoring method, device and system for hydraulic turbine set | |
CN117609836A (en) | Electromagnetic sensitivity prediction and health management method for integrated module | |
CN116610998A (en) | Switch cabinet fault diagnosis method and system based on multi-mode data fusion | |
CN114444910A (en) | Electric power Internet of things-oriented edge network system health degree evaluation method | |
Zhang et al. | Complementary ensemble adaptive local iterative filtering and its application to rolling bearing fault diagnosis | |
CN113554229A (en) | Three-phase voltage unbalance abnormality detection method and device | |
CN116629843B (en) | Remote early warning and maintenance decision support system of intelligent diesel generator set | |
CN117407675A (en) | Lightning arrester leakage current prediction method based on multi-variable reconstruction combined dynamic weight | |
CN117191147A (en) | Flood discharge dam water level monitoring and early warning method and system | |
CN116881661A (en) | Performance automatic analysis method and system based on low-voltage power capacitor |
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 |