CN116773961A - Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis - Google Patents
Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis Download PDFInfo
- Publication number
- CN116773961A CN116773961A CN202310716325.9A CN202310716325A CN116773961A CN 116773961 A CN116773961 A CN 116773961A CN 202310716325 A CN202310716325 A CN 202310716325A CN 116773961 A CN116773961 A CN 116773961A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- power transmission
- corrosion
- model
- frequency
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 123
- 230000007797 corrosion Effects 0.000 title claims abstract description 112
- 238000005260 corrosion Methods 0.000 title claims abstract description 112
- 238000001514 detection method Methods 0.000 title claims abstract description 60
- 238000004458 analytical method Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 65
- 238000012706 support-vector machine Methods 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 33
- 238000012360 testing method Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000002790 cross-validation Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 4
- 239000000284 extract Substances 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000007637 random forest analysis Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011179 visual inspection 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
- 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
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/14—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object using acoustic emission techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biochemistry (AREA)
- Evolutionary Biology (AREA)
- Analytical Chemistry (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention discloses a power transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis, which utilizes a high-frequency sensor to realize high-frequency signal acquisition of a power transmission line, extracts high-frequency characteristics from vibration signals, analyzes signal waveform characteristics, extracts high-frequency vibration signal characteristic parameters reflecting power transmission line corrosion through Fourier transform analysis, establishes a corrosion characteristic parameter model and a power transmission line corrosion identification model, accurately identifies the severity of power transmission line corrosion, and realizes detection, evaluation and early warning of potential power transmission line corrosion hazards. Compared with the traditional method for detecting the corrosion of the power transmission line, the method has the advantages of high detection speed, high detection accuracy, no power failure and the like, and can realize the online real-time monitoring of the power transmission line.
Description
Technical Field
The invention relates to the technical field of transmission line detection, in particular to a transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis.
Background
Corrosion problems of transmission lines are one of the common difficulties in power systems. The severity of the corrosion degree can have an important influence on the safe operation and the service life of the power transmission line, so that the development of a rapid and accurate power transmission line corrosion detection method is important for the safe and stable operation of a power system. However, the conventional method for detecting the corrosion of the power transmission line, such as visual inspection, chemical analysis, metallographic analysis and the like, has a plurality of limitations, such as low detection efficiency, poor accuracy, power failure requirement and the like, and cannot meet the requirements of a modern power system. If the existing transmission line corrosion detection method is low in detection efficiency and poor in accuracy, whether the transmission line is corroded or not is difficult to judge, power failure is often needed in the detection process, the chemical analysis mode is time-consuming and labor-consuming, and certain interference and risk are brought to the line for contact detection.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides a transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis, which can solve the problems of low detection efficiency and poor accuracy existing in the transmission line corrosion detection method in the prior art.
The specific technical scheme is as follows:
a transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis comprises the following steps:
s1, collecting a high-frequency vibration signal from a power transmission line by using a sensor;
s2, extracting high-frequency characteristics from the vibration signals;
step S3, selecting characteristics, which comprises the following steps:
the correlation between each feature and the transmission line corrosion level is calculated as follows:
wherein x represents vibration signal of the transmission line, y represents corrosion degree related characteristic, r xy Represents the correlation coefficient between x and y, n represents the number of samples, x i And y is i The values of x and y representing the ith data point in the sample,and->Mean values of x and y are represented respectively;
redundant features are eliminated by calculating a correlation matrix between all features and deleting features with high correlation, the calculation formula is as follows:
wherein ρ is i,j Representing the pearson correlation coefficient between the ith feature and the jth feature, cov (x i ,x j ) Representing the covariance of the ith feature and the jth feature,standard deviation, mu, representing the ith feature i Mean value representing the ith feature;standard deviation, mu, of the j-th feature j Mean value representing the j-th feature; x is x i And y is i Respectively representing the values of x and y of an ith data point in a sample; x is x j And y is j Respectively representing the values of x and y of the jth data point in the sample; after calculating correlation coefficients between every two features, a correlation matrix can be formed;
applying a feature selection algorithm to select the most relevant features contributing to corrosion detection accuracy;
s4, establishing a model;
step S5, grading the corrosion degree, obtaining a model capable of judging the corrosion degree of the power transmission line after model training and testing, setting a threshold value, and generating an alarm or a notice if the test result shows that the corrosion degree of the power transmission line exceeds the threshold value so as to realize corrosion detection of the power transmission line.
Further, the collecting of the dither signal from the transmission line using the sensor includes signal acquisition and dither signal preprocessing; the signal acquisition is to acquire a high-frequency vibration signal of the power transmission line and transmit the signal to a data acquisition system; the high-frequency signal preprocessing is to filter and denoise the collected high-frequency signal.
Further, the high frequency signal preprocessing includes:
1) The digital high-pass filtering is adopted, the acquired digital signals are input into the digital high-pass filter for filtering treatment, and the method specifically comprises the following steps: determining the cut-off frequency and the filter type of the digital high-pass filter, and representing the digital high-pass filter as a differential equation, wherein for a first-order high-pass filter, the differential equation is represented as:
y[n]＝b0*x[n]+b1*x[n-1]+b2*x[n-2]+...-a1*y[n-1]-a2*y[n-2]-...
wherein y [ n ] represents the current sample of the output signal, x [ n ] represents the current sample of the input signal, coefficients b0, b1, b2,..; the difference equation is used to calculate each sample of the output signal in a recursive manner as follows:
s11, initializing a filter state, and setting the initial states of input and output signals to zero, namely x [ n ] =0 and y [ n ] =0;
s12, recursively calculating output signals, and calculating corresponding output signal samples y [ n ] according to a difference equation for samples x [ n ] of each input signal; then updating the states of the input and output signals, namely storing the current sample as the previous sample of the next calculation so as to be used in the next iteration;
s13, repeating the step S12 until all input signal samples are processed, and sequentially processing each sample of the input signal through recursive calculation, so that the direct realization of the digital high-pass filter can be realized.
2) Noise reduction processing is carried out on signals, wavelet denoising is adopted, and the noise reduction processing comprises the following steps: selecting a proper wavelet basis function; performing wavelet decomposition on the original signal; thresholding each wavelet component; and reconstructing the processed wavelet component.
Further, the extracting the high-frequency characteristic from the vibration signal in step S2 is to extract the high-frequency characteristic from the signal by fourier transform time-frequency analysis, and obtain a characteristic parameter related to corrosion of the power transmission line, including:
1) Extracting time domain features: in the time domain, the selected characteristics comprise mean, variance, standard deviation, peak value and peak value, so that the amplitude, waveform, peak value and fluctuation characteristics of the signals are described through the characteristics;
2) Extracting frequency domain features: in the frequency domain, converting the time domain signal into a frequency domain signal through Fourier transformation, and further extracting frequency domain characteristics; the frequency domain features selected include power spectral density, frequency bandwidth, frequency peak, energy, so as to describe the features of the signal at different frequencies through the features.
Further, the modeling includes using a Support Vector Machine (SVM) to build a classification model, taking the features selected by the preamble as input features of the model, taking the corrosion degree of the power transmission line as an output result of the model, and performing corrosion detection on the power transmission line through the model obtained by training.
Further, the establishment of the SVM model comprises two stages of training and prediction;
in the training stage, searching an optimal segmentation hyperplane by using an SVM algorithm according to the existing sample data, and determining parameters of the hyperplane;
in the prediction stage, the test samples are mapped to a high-dimensional space, and the test samples are classified by using the optimal hyperplane obtained through training.
Further, the specific model building step includes:
s41, data preparation and preprocessing: collecting and sorting a training data set with labels, and ensuring that each sample has a corresponding feature vector and category label; selecting the features, and performing necessary data preprocessing operations to ensure that the features are on the same scale;
s42, dividing the data set: dividing a data set into a training set and a testing set, adopting a random division or cross-validation method, wherein the training set is used for training parameters of an SVM model, and the testing set is used for evaluating performance and generalization capability of the model;
s43, model training: invoking an SVM library or tool to establish an SVM model, and selecting a Gaussian radial basis function as a kernel function in the SVM model; setting a regularization parameter C; setting a bandwidth parameter of a Gaussian kernel function, which is also called a gamma value;
s44, parameter tuning: performing parameter tuning by using a cross-validation method to select the optimal combination of C and gamma values; selecting the best performing parameter combination on the test set by trying different parameter combinations and evaluating the performance of each combination using cross-validation;
s45, evaluating a model: evaluating the trained SVM model by using the test set data;
s46, model application: classifying or carrying out regression prediction on the new unknown sample by using the trained SVM model; for the classification problem, inputting the feature vector of the new unknown sample into a trained SVM model, and outputting a predicted class label according to a classification decision function of the model; for the regression problem, the SVM model is used as a support vector regression model.
Further, the method also comprises the following steps:
s47, model tuning and improvement: if the performance of the model is not in accordance with the expectations, the model is optimized and improved by adopting at least one of the following methods: firstly, adjusting regularization parameters C and bandwidth parameters gamma of a Gaussian kernel function to find a better balance point; extracting the characteristics with more information quantity by using a characteristic engineering technology, or trying other kernel functions to carry out nonlinear mapping; and thirdly, combining a plurality of SVM models by using an integrated learning method so as to further improve the performance.
Further, in step S5, the corrosion levels are divided into 5 levels, namely, 0 level, 1 level, 2 level, 3 level and 4 level, the corrosion levels are increased from 0 level to 4 level, wherein 0 level indicates no corrosion, 4 level indicates the most serious corrosion, a model capable of judging the corrosion level of the power transmission line is obtained through model training and testing, the threshold value is set to be 2.5, and if the test result shows that the corrosion level of the power transmission line exceeds the threshold value, an alarm or notification is generated to realize the corrosion detection of the power transmission line.
Further, on-site maintenance and processing are carried out according to the signals pre-warned by the detection model in the step S5, and further correction and optimization are carried out on the detection model through the actual maintenance processing result.
With the continuous development of sensor technology and high-speed signal processing technology, transmission line corrosion detection by utilizing high-frequency signal characteristics becomes a new research direction. The invention discloses a transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis.
When the power transmission line is acted by external force such as wind, the power transmission line can generate certain vibration, the vibration can form some ripples or wave deformation on the power transmission line, the surface of the power transmission line is not smooth due to corrosion, the friction resistance of the power transmission line is increased during vibration, and therefore the natural frequency and wind vibration resistance of the power transmission line are reduced. Therefore, the higher the corrosion of the power transmission line is, the lower the wind vibration resistance of the power transmission line is, and the vibration is easy to occur, so that the stability and the safety of a power system are affected. The method for detecting the corrosion of the power transmission line based on the vibration signal high-frequency characteristic analysis can realize the high-frequency signal acquisition of the power transmission line by utilizing a high-frequency sensor, extract the high-frequency vibration signal characteristic parameters reflecting the corrosion of the power transmission line by analyzing the waveform characteristics of the signals and analyzing by Fourier transformation, establish a corrosion characteristic parameter model and a power transmission line corrosion identification model, accurately identify the severity of the corrosion of the power transmission line and realize the detection, evaluation and early warning of the corrosion hidden danger of the power transmission line. Compared with the traditional method for detecting the corrosion of the power transmission line, the method has the advantages of high detection speed, high detection accuracy, no power failure and the like, and can realize the online real-time monitoring of the power transmission line.
The method has the characteristics of non-contact, high efficiency, accuracy and the like, and can realize rapid and accurate detection of the corrosion degree of the power transmission line. The method mainly utilizes vibration signal analysis, and extracts corrosion characteristic information contained in the high-frequency characteristic of the vibration signal of the power transmission line by analyzing the high-frequency characteristic. Specifically, the method collects vibration signals of the power transmission line, filters low-frequency components by using a digital high-pass filter, and then performs power spectrum analysis on high-frequency signals to extract characteristic parameters of a frequency domain. And then, a classification model is established by using a machine learning method such as a Support Vector Machine (SVM) and the like, and the power transmission lines with different corrosion degrees are classified. Finally, judging and early warning the corrosion degree according to the classification result.
Compared with the prior art, the invention has the beneficial effects that:
the method for detecting the corrosion of the power transmission line based on the high-frequency characteristic analysis of the vibration signal can be used for detecting the corrosion condition of the power transmission line and carrying out corresponding maintenance and protection measures according to the detection result, so that the service life of the power transmission line is prolonged. In addition, in the design and manufacturing process of the power transmission line, the method can be used for detecting and evaluating the quality of the power transmission line and ensuring the safe and reliable operation of the power transmission line, so that the detection method has a very wide application prospect in the field of power systems. The following advantages and benefits can be obtained by using the transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis:
1. high efficiency and accuracy: according to the method, the corrosion condition of the power transmission line can be rapidly and accurately detected by analyzing the high-frequency characteristics of the vibration signals, so that the time and labor consuming steps such as power failure, chemical analysis and the like in the traditional method are avoided;
2. non-contact detection: the detection method based on the vibration signal does not need to directly contact the power transmission line, but collects and analyzes the vibration signal through equipment such as a sensor, so that the non-contact detection of the line is realized, and the interference and risk of the line are reduced;
3. the application is wide: the method is not only suitable for maintenance and protection of the power transmission line, but also can be applied to the design and manufacturing process of the power transmission line; the quality detection of the newly-built circuit can ensure the safe and reliable operation of the circuit and improve the stability and reliability of the power system;
4. data driving: the modeling process based on the machine learning method can train and optimize the model according to the actual data, so that the model can be better adapted to corrosion characteristics of different lines, and the accuracy and reliability of prediction are improved;
5. real-time monitoring and early warning: the method can realize real-time monitoring of the power transmission line and timely send out an early warning signal so as to take corresponding maintenance and protection measures and avoid potential safety hazards and line faults caused by corrosion problems.
In summary, the transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis has important application value in the power system. By the method, the corrosion condition of the power transmission line can be accurately detected and early-warned, the safety and reliability of the line are improved, and the method contributes to the stable operation and the service life extension of the power system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
Fig. 1 is a schematic flow chart of a method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of a vibration signal.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1, a preferred embodiment of the present invention provides a method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of a vibration signal, the method comprising the following steps:
and S1, collecting a high-frequency vibration signal from the power transmission line by using a sensor.
The step of collecting the high-frequency vibration signals from the power transmission line by using the sensor comprises signal acquisition and high-frequency signal preprocessing; the signal acquisition is to acquire a high-frequency vibration signal of the power transmission line and transmit the signal to a data acquisition system; the high-frequency signal preprocessing is to filter and denoise the collected high-frequency signal.
The utility model provides a signal acquisition and high frequency signal preprocessing, specifically, install vibration sensor on transmission line, gather transmission line's high frequency vibration signal to with signal transmission to data acquisition system, convert transmission line vibration signal into the electrical signal, and with its transmission to data acquisition system, including:
selecting proper vibration sensor types and specifications according to factors such as the type of a power transmission line, voltage class, line structure, working environment and the like;
selecting proper sensor mounting positions and methods according to different parts and structures of a power transmission line, and selecting to mount vibration sensors on wires;
carrying out corresponding signal processing and filtering on the high-frequency signal of the power transmission line; in the acquisition process, the factors such as the working state of the line, environmental noise and the like are required to be considered, and the proper sampling rate and sampling depth are adopted so as to ensure the accuracy and reliability of the acquired signals;
signal processing and analysis are carried out on the collected signal data, and useful characteristic information is extracted; vibration characteristics of the circuit are obtained through methods such as signal spectrum analysis and time domain analysis, and therefore the working state and the health condition of the circuit are judged.
Further, the high-frequency signal preprocessing is to perform preprocessing such as filtering and denoising on the collected high-frequency signals, so that the quality of the signals is improved. And filtering the acquired signals to remove noise and interference therein, so that the signals are more stable and accurate. The method specifically comprises the following steps:
1) And (3) adopting digital high-pass filtering, and inputting the acquired digital signals into a digital high-pass filter for filtering treatment.
In the processing, different filter types and cut-off frequencies, and different orders are selected to obtain different filtering effects, and a direct implementation based on a differential equation is adopted, and the method represents the digital high-pass filter as a differential equation, wherein the relation between an input signal and an output signal can be represented by recursion. The method specifically comprises the following steps: first, the cut-off frequency and the filter type of the digital high-pass filter, such as a first-order high-pass filter or a second-order high-pass filter, are determined, and then the digital high-pass filter is expressed as a differential equation, and for the first-order high-pass filter, the differential equation can be expressed as:
y[n]＝b0*x[n]+b1*x[n-1]+b2*x[n-2]+...-a1*y[n-1]-a2*y[n-2]-...
wherein y n represents the current sample of the output signal, x n represents the current sample of the input signal, y n-1 and y n-2 represent the first two samples of the output signal, x n-1 and x n-2 represent the first two samples of the input signal; coefficients b0, b1, b 2..are the weighting coefficients of the input signal, a1, a 2..are the weighting coefficients of the output signal, coefficients in the differential equation are determined according to the filter type and specification selected, these coefficients directly affecting the frequency response and characteristics of the filter. The difference equation is used to calculate each sample of the output signal in a recursive manner as follows:
s11, initializing a filter state, and setting the initial states of input and output signals to zero, namely x [ n ] =0 and y [ n ] =0;
s12, recursively calculating output signals, and calculating corresponding output signal samples y [ n ] according to a difference equation for samples x [ n ] of each input signal; then updating the states of the input and output signals, namely storing the current sample as the previous sample of the next calculation so as to be used in the next iteration;
s13, repeating the step S12 until all input signal samples are processed, and sequentially processing each sample of the input signal through recursive calculation, so that the direct realization of the digital high-pass filter can be realized.
2) Noise reduction processing is carried out on the signals so as to remove noise and interference in the signals, so that the signals are clearer and more reliable.
Denoising with wavelet, comprising:
selecting a proper wavelet basis function: the wavelet base functions have different properties in different frequency ranges, so that proper wavelet base functions need to be selected according to signal characteristics and denoising effects;
wavelet decomposition is performed on the original signal: decomposing the original signal into wavelet components of different frequencies, each wavelet component corresponding to a different scale and frequency;
each wavelet component is then thresholded: filtering and thresholding each wavelet component to remove noise signals therein;
and finally reconstructing the processed wavelet component: and reconstructing the processed wavelet component to obtain a denoised signal.
And S2, extracting high-frequency characteristics from the vibration signals.
The step of extracting high-frequency characteristics from the vibration signal is to extract the high-frequency characteristics of the signal by adopting Fourier transform time-frequency analysis, and the step of obtaining characteristic parameters related to corrosion of the power transmission line comprises the following steps:
1) Extracting time domain features: in the time domain, the selected characteristics comprise mean, variance, standard deviation, peak value and the like, so that the amplitude, waveform, peak value and fluctuation characteristics of the signals are described through the characteristics;
2) Extracting frequency domain features: in the frequency domain, converting the time domain signal into a frequency domain signal through Fourier transformation, and further extracting frequency domain characteristics; the frequency domain features selected include power spectral density, frequency bandwidth, frequency peak, energy, etc., so that the features described above can be used to characterize the signal at different frequencies.
And S3, selecting characteristics.
The selection of the characteristics comprises:
the correlation between each feature and the transmission line corrosion level is calculated as follows:
wherein x represents vibration signal of the transmission line, y represents corrosion degree related characteristic, r xy Represents the correlation coefficient between x and y, n represents the number of samples, x i And y is i The values of x and y representing the ith data point in the sample,and->Mean values of x and y are represented respectively;
redundant features are eliminated by calculating a correlation matrix between all features and deleting features with high correlation, the calculation formula is as follows:
wherein ρ is i,j Representing the pearson correlation coefficient between the ith feature and the jth feature, cov (x i ,x j ) Representing the covariance of the ith feature and the jth feature,standard deviation, mu, representing the ith feature i Mean value representing the ith feature;standard deviation, mu, of the j-th feature j Mean value representing the j-th feature; x is x i And y is i Respectively representing the values of x and y of an ith data point in a sample; x is x j And y is j Respectively representing the values of x and y of the jth data point in the sample; and calculating correlation coefficients between every two features to form a correlation matrix.
A feature selection algorithm (random forest algorithm) is applied to select the most relevant features contributing to the accuracy of corrosion detection.
The characteristic selection process is a continuous screening and optimizing process, and needs to comprehensively consider correlation, relation among characteristics and algorithm requirements, and select the characteristics which can represent the corrosion degree most. The method comprises the following steps: and collecting vibration signals of the power transmission line within a period of time, and obtaining characteristics related to the corrosion degree of the line by using a high-frequency characteristic analysis method. And (3) adopting a random forest algorithm to select the characteristics, and finally selecting the peak value, the frequency, the energy and the like.
And S4, establishing a model.
The method comprises the steps of establishing a model, namely establishing a classification model by using a Support Vector Machine (SVM), taking the selected characteristics as input characteristics of the model, taking the corrosion degree of the power transmission line as an output result of the model, and carrying out corrosion detection on the power transmission line through the model obtained through training.
The building of the SVM model comprises two stages of training and prediction;
in the training stage, according to the existing sample data, an SVM algorithm is used for searching the optimal segmentation hyperplane, and parameters of the hyperplane are determined.
In the prediction stage, the test samples are mapped to a high-dimensional space, and the test samples are classified by using the optimal hyperplane obtained through training.
The key of the SVM algorithm is to select a kernel function, which is used for mapping the sample to a high-dimensional space, and a Gaussian radial basis function is adopted, so that the SVM algorithm has better flexibility and applicability and can obtain better classification effect. Polynomial kernel functions and linear kernel functions are more suitable for some specific problems, for example polynomial kernel functions are suitable for periodic patterns in nonlinear problems, while linear kernel functions are suitable for situations with higher feature dimensions and larger data volumes.
In a preferred embodiment, the specific modeling step comprises:
s41, data preparation and preprocessing: collecting and sorting a training data set with labels, and ensuring that each sample has a corresponding feature vector and category label; selecting the characteristics, and selecting the characteristics based on the method in the step S3; finally, carrying out necessary data preprocessing operations such as feature scaling, normalization, missing value processing and the like so as to ensure that the features are on the same scale;
s42, dividing the data set: dividing a data set into a training set and a testing set, adopting a random division or cross-validation method, wherein the training set is used for training parameters of an SVM model, and the testing set is used for evaluating performance and generalization capability of the model;
s43, model training: firstly, an SVM library or tool is called to establish an SVM model, a Gaussian radial basis function is selected in the SVM model to serve as a kernel function, and the Gaussian kernel function has nonlinear mapping capability and can be used for solving nonlinear problems; then, a regularization parameter C is set, the regularization parameter C controls the complexity and fault tolerance of the model, a smaller C value can generate larger intervals, classification errors can be caused, a larger C value can generate smaller intervals, and classification correctness can be emphasized more; finally, setting bandwidth parameters of the Gaussian kernel function, which are also called gamma values, wherein the larger the gamma value is, the smaller the action range of the Gaussian kernel function is, the decision boundary is more concerned with data points which are closer to the support vector, and the smaller the gamma value is, the larger the action range of the Gaussian kernel function is, and the decision boundary is smoother;
s44, parameter tuning: firstly, performing parameter tuning by using a cross-validation method to select the optimal combination of C and gamma values; then, by trying different combinations of parameters and using cross-validation to evaluate the performance of each combination, the combination of parameters that performs best on the test set is selected;
s45, evaluating a model: evaluating the trained SVM model by using the test set data; calculating common classification evaluation indexes such as accuracy, precision, recall, F1 score and the like to evaluate the performance and generalization capability of the model;
s46, model application: firstly, classifying or carrying out regression prediction on a new unknown sample by using a trained SVM model; then, for the classification problem, inputting the feature vector of the new unknown sample into a trained SVM model, and outputting a predicted class label according to a classification decision function of the model; finally, for regression problems, the SVM model can be used as a support vector regression (Support Vector Regression, SVR) model, with SVR using principles similar to classification problems, but with the goal of fitting a function to predict the value of a continuous target variable;
s47, model tuning and improvement: if the performance of the model is not in line with the expectations, the model can be optimized and improved by adopting at least one of the following methods: firstly, adjusting regularization parameters C and bandwidth parameters gamma of a Gaussian kernel function to find a better balance point; extracting the characteristics with more information quantity by using a characteristic engineering technology, or trying other kernel functions to carry out nonlinear mapping; and thirdly, combining a plurality of SVM models by using an integrated learning method, such as random forest, boosting and the like, so as to further improve the performance.
Step S5, grading the corrosion degree, obtaining a model capable of judging the corrosion degree of the power transmission line after model training and testing, setting a threshold value, and generating an alarm or a notice if the test result shows that the corrosion degree of the power transmission line exceeds the threshold value so as to realize corrosion detection of the power transmission line.
In a specific embodiment, the corrosion degree is divided into 5 grades, namely 0 grade, 1 grade, 2 grade, 3 grade and 4 grade, the corrosion degree is increased from 0 grade to 4 grade in sequence, for example, 0 grade indicates no corrosion, 4 grade indicates the most serious corrosion, a model capable of judging the corrosion degree of the power transmission line is obtained through model training and testing, the threshold value is set to be 2.5 (grade), and if the test result shows that the corrosion degree of the power transmission line exceeds the threshold value of 2.5 (grade), an alarm or notification is generated to realize the corrosion detection of the power transmission line. And when the corrosion abnormality is found, an early warning signal is sent out in time to inform maintenance personnel to further check and repair so as to carry out corresponding repair and treatment.
And (3) carrying out on-site maintenance and processing on signals pre-warned by the detection model, and further correcting and optimizing the detection model through an actual maintenance processing result, thereby improving the accuracy and reliability of the corrosion detection model of the power transmission line.
According to the method, the corrosion degree of the power transmission line can be judged by collecting the vibration signals of the power transmission line, preprocessing, feature extraction, feature selection and model establishment, and the accuracy and the efficiency of corrosion detection are improved. In particular overview, the method of the present invention has at least the following effects compared to the prior art:
firstly, the detection accuracy is improved, the corrosion degree of the power transmission line can be judged more accurately by adopting a vibration signal high-frequency characteristic analysis method, the misjudgment and missed judgment in the traditional method are avoided, and the detection accuracy is improved;
secondly, the detection efficiency is improved, the vibration signals can be collected and processed more rapidly based on the vibration signal high-frequency characteristic analysis method, and automatic corrosion detection is carried out through characteristic selection and model establishment, so that the detection efficiency is improved.
Table 1 shows comparison of the accuracy of the various methods.
Table 1 comparison of test accuracy for different methods
As can be seen from Table 1, the detection rate of the method is higher, so that the detection effect is better, the method does not need power failure operation, time and labor are saved, and the method is non-contact detection, so that the interference and risk of a circuit are reduced.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (10)
1. The method for detecting the corrosion of the power transmission line based on the high-frequency characteristic analysis of the vibration signal is characterized by comprising the following steps of:
s1, collecting a high-frequency vibration signal from a power transmission line by using a sensor;
s2, extracting high-frequency characteristics from the vibration signals;
step S3, selecting characteristics, which comprises the following steps:
the correlation between each feature and the transmission line corrosion level is calculated as follows:
wherein x represents vibration signal of the transmission line, y represents corrosion degree related characteristic, r xy Represents the correlation coefficient between x and y, n represents the number of samples, x i And y is i The values of x and y representing the ith data point in the sample,and->Mean values of x and y are represented respectively;
redundant features are eliminated by calculating a correlation matrix between all features and deleting features with high correlation, the calculation formula is as follows:
wherein ρ is i,j Representing the pearson correlation coefficient between the ith feature and the jth feature, cov (x i ,x j ) Representing the covariance of the ith feature and the jth feature,standard deviation, mu, representing the ith feature i Mean value representing the ith feature; />Standard deviation, mu, of the j-th feature j Mean value representing the j-th feature; x is x i And y is i Respectively representing the values of x and y of an ith data point in a sample; x is x j And y is j Respectively representing the values of x and y of the jth data point in the sample; after calculating correlation coefficients between every two features, a correlation matrix can be formed;
applying a feature selection algorithm to select the most relevant features contributing to corrosion detection accuracy;
s4, establishing a model;
step S5, grading the corrosion degree, obtaining a model capable of judging the corrosion degree of the power transmission line after model training and testing, setting a threshold value, and generating an alarm or a notice if the test result shows that the corrosion degree of the power transmission line exceeds the threshold value so as to realize corrosion detection of the power transmission line.
2. The method for detecting corrosion of the power transmission line based on high-frequency characteristic analysis of vibration signals according to claim 1, wherein the step of collecting the high-frequency vibration signals from the power transmission line by using the sensor comprises signal acquisition and high-frequency signal preprocessing; the signal acquisition is to acquire a high-frequency vibration signal of the power transmission line and transmit the signal to a data acquisition system; the high-frequency signal preprocessing is to filter and denoise the collected high-frequency signal.
3. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of a vibration signal according to claim 2, wherein the high-frequency signal preprocessing includes:
1) The digital high-pass filtering is adopted, the acquired digital signals are input into the digital high-pass filter for filtering treatment, and the method specifically comprises the following steps: determining the cut-off frequency and the filter type of the digital high-pass filter, and representing the digital high-pass filter as a differential equation, wherein for a first-order high-pass filter, the differential equation is represented as:
y[n]＝b0*x[n]+b1*x[n-1]+b2*x[n-2]+...-a1*y[n-1]-a2*y[n-2]-...
wherein y [ n ] represents the current sample of the output signal, x [ n ] represents the current sample of the input signal, coefficients b0, b1, b2,..; the difference equation is used to calculate each sample of the output signal in a recursive manner as follows:
s11, initializing a filter state, and setting the initial states of input and output signals to zero, namely x [ n ] =0 and y [ n ] =0;
s12, recursively calculating output signals, and calculating corresponding output signal samples y [ n ] according to a difference equation for samples x [ n ] of each input signal; then updating the states of the input and output signals, namely storing the current sample as the previous sample of the next calculation so as to be used in the next iteration;
s13, repeating the step S12 until all input signal samples are processed, and sequentially processing each sample of the input signal through recursive calculation, so that the direct realization of the digital high-pass filter can be realized.
2) Noise reduction processing is carried out on signals, wavelet denoising is adopted, and the noise reduction processing comprises the following steps: selecting a proper wavelet basis function; performing wavelet decomposition on the original signal; thresholding each wavelet component; and reconstructing the processed wavelet component.
4. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of a vibration signal according to claim 1, wherein the extracting the high-frequency characteristic from the vibration signal in step S2 is to extract the high-frequency characteristic from the signal by fourier transform time-frequency analysis, and the obtaining the characteristic parameter related to corrosion of the power transmission line includes:
1) Extracting time domain features: in the time domain, the selected characteristics comprise mean, variance, standard deviation, peak value and peak value, so that the amplitude, waveform, peak value and fluctuation characteristics of the signals are described through the characteristics;
2) Extracting frequency domain features: in the frequency domain, converting the time domain signal into a frequency domain signal through Fourier transformation, and further extracting frequency domain characteristics; the frequency domain features selected include power spectral density, frequency bandwidth, frequency peak, energy, so as to describe the features of the signal at different frequencies through the features.
5. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of vibration signals according to claim 1, wherein the modeling includes using a Support Vector Machine (SVM) to build a classification model, using a previously selected characteristic as an input characteristic of the model, using a corrosion degree of the power transmission line as an output result of the model, and performing corrosion detection on the power transmission line by training the obtained model.
6. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of vibration signals according to claim 1, wherein the establishment of the SVM model comprises two stages of training and prediction;
in the training stage, searching an optimal segmentation hyperplane by using an SVM algorithm according to the existing sample data, and determining parameters of the hyperplane;
in the prediction stage, the test samples are mapped to a high-dimensional space, and the test samples are classified by using the optimal hyperplane obtained through training.
7. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of vibration signals according to claim 1, 5 or 6, wherein the specific model building step comprises:
s41, data preparation and preprocessing: collecting and sorting a training data set with labels, and ensuring that each sample has a corresponding feature vector and category label; selecting the features, and performing necessary data preprocessing operations to ensure that the features are on the same scale;
s42, dividing the data set: dividing a data set into a training set and a testing set, adopting a random division or cross-validation method, wherein the training set is used for training parameters of an SVM model, and the testing set is used for evaluating performance and generalization capability of the model;
s43, model training: invoking an SVM library or tool to establish an SVM model, and selecting a Gaussian radial basis function as a kernel function in the SVM model; setting a regularization parameter C; setting a bandwidth parameter of a Gaussian kernel function, which is also called a gamma value;
s44, parameter tuning: performing parameter tuning by using a cross-validation method to select the optimal combination of C and gamma values; selecting the best performing parameter combination on the test set by trying different parameter combinations and evaluating the performance of each combination using cross-validation;
s45, evaluating a model: evaluating the trained SVM model by using the test set data;
s46, model application: classifying or carrying out regression prediction on the new unknown sample by using the trained SVM model; for the classification problem, inputting the feature vector of the new unknown sample into a trained SVM model, and outputting a predicted class label according to a classification decision function of the model; for the regression problem, the SVM model is used as a support vector regression model.
8. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of a vibration signal according to claim 7, further comprising:
s47, model tuning and improvement: if the performance of the model is not in accordance with the expectations, the model is optimized and improved by adopting at least one of the following methods: firstly, adjusting regularization parameters C and bandwidth parameters gamma of a Gaussian kernel function to find a better balance point; extracting the characteristics with more information quantity by using a characteristic engineering technology, or trying other kernel functions to carry out nonlinear mapping; and thirdly, combining a plurality of SVM models by using an integrated learning method so as to further improve the performance.
9. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of vibration signals according to claim 1, wherein in step S5, the corrosion levels are classified into 5 levels, namely, 0 level, 1 level, 2 level, 3 level and 4 level, the corrosion levels are increased from 0 level to 4 level in sequence, wherein 0 level indicates no corrosion, 4 level indicates the most serious corrosion, a model capable of judging the corrosion level of the power transmission line is obtained through model training and testing, a threshold value is set to be 2.5, and an alarm or notification is generated to realize corrosion detection of the power transmission line if the test result shows that the corrosion level of the power transmission line exceeds the threshold value.
10. The method for detecting corrosion of a power transmission line based on high-frequency characteristic analysis of vibration signals according to claim 1, wherein the on-site maintenance and processing are performed according to the signals pre-warned by the detection model in step S5, and the detection model is further corrected and optimized according to the actual maintenance processing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310716325.9A CN116773961A (en) | 2023-06-16 | 2023-06-16 | Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310716325.9A CN116773961A (en) | 2023-06-16 | 2023-06-16 | Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116773961A true CN116773961A (en) | 2023-09-19 |
Family
ID=87985292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310716325.9A Pending CN116773961A (en) | 2023-06-16 | 2023-06-16 | Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116773961A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272030A (en) * | 2023-11-20 | 2023-12-22 | 南通市计量检定测试所 | Method for sampling and processing dynamic signal packet |
-
2023
- 2023-06-16 CN CN202310716325.9A patent/CN116773961A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272030A (en) * | 2023-11-20 | 2023-12-22 | 南通市计量检定测试所 | Method for sampling and processing dynamic signal packet |
| CN117272030B (en) * | 2023-11-20 | 2024-01-26 | 南通市计量检定测试所 | Method for sampling and processing dynamic signal packet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11022633B2 (en) | Enhanced system and method for conducting PCA analysis on data signals | |
| Wen et al. | Graph modeling of singular values for early fault detection and diagnosis of rolling element bearings | |
| CN107657088B (en) | Rolling bearing fault diagnosis method based on MCKD algorithm and support vector machine | |
| CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
| CN102016607B (en) | Method and apparatus for analyzing waveform signals of a power system | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN102155988B (en) | Equipment monitoring and diagnosing method | |
| CN116773961A (en) | Transmission line corrosion detection method based on vibration signal high-frequency characteristic analysis | |
| CN114563150A (en) | Bridge health online detection module generation method, detection method, tool box and device | |
| CN112213687B (en) | Gateway electric energy meter data anomaly detection method and system based on pseudo-anomaly point identification | |
| CN112207631B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| CN116380445A (en) | Equipment state diagnosis method and related device based on vibration waveform | |
| CN111291918B (en) | Rotating machine degradation trend prediction method based on stationary subspace exogenous vector autoregression | |
| CN116124398A (en) | Rotary machine fault detection method and device, equipment and storage medium | |
| Yang et al. | Early change detection in dynamical bearing degradation process based on hierarchical graph model and adaptive inputs weighting fusion | |
| CN110956112B (en) | Novel high-reliability slewing bearing service life assessment method | |
| CN112016800A (en) | Feature selection method and system based on effectiveness index | |
| CN113139430A (en) | Acoustic signal analysis method for fault detection, and method and device for fault detection | |
| Yao et al. | A framework via impulses-oriented Gini index and extreme value distribution for rolling bearing dynamic fault alarm and identification | |
| CN117435908A (en) | Multi-fault feature extraction method for rotary machine | |
| CN112215307A (en) | Method for automatically detecting signal abnormality of seismic instrument by applying machine learning | |
| CN109840386B (en) | Damage identification method based on factor analysis | |
| CN116482526A (en) | Analysis system for non-fault phase impedance relay | |
| CN116610990A (en) | Method and device for identifying hidden danger of breaker based on characteristic space differentiation | |
| CN113408383B (en) | Audible noise invalid data judgment method based on bounded beta (g, h) distribution and MWKPCA |
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 |