CN114679216A - Algorithm and device for improving analysis precision based on OTDR - Google Patents

Algorithm and device for improving analysis precision based on OTDR Download PDF

Info

Publication number
CN114679216A
CN114679216A CN202210385889.4A CN202210385889A CN114679216A CN 114679216 A CN114679216 A CN 114679216A CN 202210385889 A CN202210385889 A CN 202210385889A CN 114679216 A CN114679216 A CN 114679216A
Authority
CN
China
Prior art keywords
otdr
data
module
analysis
event
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210385889.4A
Other languages
Chinese (zh)
Inventor
黄中华
陆宁海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Wenadi Information Technology Co ltd
Original Assignee
Jiangsu Wenadi Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Wenadi Information Technology Co ltd filed Critical Jiangsu Wenadi Information Technology Co ltd
Priority to CN202210385889.4A priority Critical patent/CN114679216A/en
Publication of CN114679216A publication Critical patent/CN114679216A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
    • H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
    • H04B10/071—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using a reflected signal, e.g. using optical time domain reflectometers [OTDR]
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Electromagnetism (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Testing Of Optical Devices Or Fibers (AREA)

Abstract

The invention relates to the technical field of power communication, and discloses an algorithm and a device for improving analysis accuracy based on OTDR (optical time Domain reflectometer). The method comprises the following steps of carrying out multiple measurements on an optical fiber line by adopting OTDR, obtaining OTDR curve data of the optical fiber line, carrying out pretreatment on subsequent data analysis, carrying out denoising treatment on the obtained OTDR data, and obtaining the OTDR curve data after denoising. According to the invention, the wavelet base DB3 modulus maximum method is adopted to perform section denoising treatment, the wavelet transformation and the least square method are adopted to analyze events for the section data after denoising, the classification and identification method of the special points of the optical fiber line of the SVM classifier is used, the OTDR data is analyzed by the method, and each special point in the OTDR curve is analyzed, so that an operator can know each special position of the optical fiber more intuitively, the OTDR test precision is greatly improved, the analysis precision is improved, and the analysis speed is further improved.

Description

Algorithm and device for improving analysis precision based on OTDR
Technical Field
The invention relates to the technical field of power communication, in particular to an algorithm and a device for improving analysis accuracy based on OTDR.
Background
With the continuous development of optical fiber communication technology, optical fibers are applied more and more widely in power system communication. The operation reliability of the optical fiber transmission network is an important guarantee for the safe production and the high-efficiency operation of the power system. The operation reliability of the optical fiber transmission network is an important guarantee for the safe production and the high-efficiency operation of the power system. With the rapid increase of data communication amount, the role of optical fiber communication is more and more important as a main transmission medium of an information highway, and once an optical fiber line fails, the safety production of a power system is seriously influenced by the interruption for a long time due to the large amount of transmission information. The current mainstream optical fiber fault detection equipment is the OTDR, and data obtained through OTDR measurement is used to analyze relevant fault points of the optical fiber and remove faults in time.
At present, the method commonly used for analyzing the OTDR data is sensitive to data noise, has larger error, and has large calculation amount, slow analysis speed and some defects.
Disclosure of Invention
In order to achieve the purpose, the invention provides the following technical scheme: an algorithm and a device for improving analysis accuracy based on OTDR (optical time Domain reflectometer), comprising the following steps of:
s1, measuring the optical fiber line for multiple times by adopting the OTDR, obtaining OTDR curve data of the optical fiber line, preprocessing the acquired OTDR data for subsequent data analysis, denoising the acquired OTDR data, and obtaining the denoised OTDR curve data, wherein the OTDR curve data preprocessing comprises constructing a fiber breaking event at the tail of the actually measured OTDR raw data as a termination event, and after the artificial termination event is added, the length of the curve data meets the length of the data required by binary wavelet transformation.
S2, processing the OTDR curve data obtained in the first step after denoising by adopting wavelet transformation to the preprocessed OTDR curve data or the denoised curve data segment, obtaining optical fiber signal characteristic points, marking the obtained optical fiber signal characteristic points, performing preliminary positioning according to the characteristics of the events on high-frequency coefficients to obtain all events to be determined, and respectively marking the events to be determined as: welding points, breaking points, starting ends, tail ends and over-bending points.
S3, calculating a line average consumption threshold, further accurately positioning an event to be determined by adopting a least square method and related parameters, determining whether curve event analysis is finished or not according to whether a reflection event with accurate positioning failure exists or not and whether OTDR curve data are subjected to noise reduction processing or not, using marked data for training an SVM classification model as a training set, using data for verifying prediction precision of the SVM classification model as a verification set, using a DB3 wavelet base wavelet transformation modulus maximum value method to perform noise reduction on an OTDR curve segment needing noise reduction, and replacing curve segment data corresponding to the original OTDR with the noise-reduced curve segment data.
S4, learning the data used for training the SVM classification model in a supervision mode to obtain a projection matrix capable of increasing the distinguishing degree of the OTDR data feature points; distributing different weights to the characteristic points in the projection matrix to obtain distance measurement, improving a Gaussian radial basis function by using the distance measurement, and establishing an improved SVM classification model, wherein the improved Gaussian radial basis function is as follows:
Figure BDA0003594972000000021
wherein
Figure BDA0003594972000000022
Is a Gaussian radial basis kernel function parameter obtained by a grid search algorithm, xi,xjRepresenting a feature vector, DM(xi,xj) Is a measure of distance, said DM(xi,xj) The construction process comprises the following steps:
setting the distance measure in projection space to:
Figure BDA0003594972000000023
||L(xi-xj)||2is L (x)i-xj) Is of two norms, [ L (x)i-xj)]TIs L (x)i-xj) Transposing the matrix, squaring the distance and representing it in matrix form, and measuring the distance DM(xi，xj)。
And S5, respectively verifying the trained SVM classification models by using a verification set, selecting the model with the highest prediction precision on the verification set as a final SVM classifier, and recognizing characteristic points of the OTDR data curve by using the SVM classifier to finally recognize the characteristic points of each position of the optical cable.
And S6, calculating the length of the optical fiber line, the total line attenuation and the average line consumption by utilizing the analyzed events.
Preferably, the length of the curve data in step S1 satisfies the length of the data required for the binary wavelet transform: l ^ sigma 2^ N, N ∈ N.
Preferably, in the high frequency coefficients in step S2, the emission event is characterized in that the corresponding high frequency coefficient value changes from a negative value to a positive value from the start point to the end point of the reflection event, and in the preliminary positioning, the negative minimum value is used as the start point of the reflection event, and the positive maximum value is used as the end point of the reflection event.
Preferably, in step S3, the OTDR curve segment to be denoised is denoised by using DB3 wavelet based wavelet transform modulo maximum.
Preferably, in the step S3, the transmission power is calculated by continuously taking N points from the end point of the start event, and obtaining a fitted straight line L by using a least square method, where an intercept of the straight line L on the optical power X axis is the transmission power, and obtaining: total line attenuation-the power at the beginning of the end of transmission event.
An algorithm device for improving analysis accuracy based on OTDR comprises a measuring module, a preprocessing module, a high-frequency coefficient module, a classification model module, a verification module and an analysis module.
Preferably, the measurement module is connected with a preprocessing module, and the preprocessing module is connected with a classification model module.
Preferably, the classification model module is connected with a verification module, and the verification module is connected with the analysis module.
The invention provides an OTDR (optical time domain reflectometer) based algorithm and device for improving analysis accuracy. The method has the following beneficial effects:
the invention adopts Haar wavelet basis to carry out discrete stationary wavelet transform on OTDR data, utilizes the characteristics of events on high-frequency coefficients, determines whether denoising is needed and determines a section needing denoising according to the positioning result of an event to be reflected, adopts a wavelet basis DB3 modulus maximum method to carry out section denoising treatment, adopts wavelet transform and a least square method again to analyze the event on the section data after denoising, and adopts a classification identification method of special points of an optical fiber line of an SVM classifier to analyze the OTDR data and analyze each special point in an OTDR curve, so that an operator can more intuitively know each special position of the optical fiber, the test precision of the OTDR is greatly improved, the analysis accuracy is improved, and the analysis speed is further improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic view of the structure of the apparatus of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
As shown in fig. 1, the present invention provides a technical solution: an algorithm and a device for improving analysis accuracy based on OTDR (optical time Domain reflectometer), comprising the following steps of:
s1, measuring the optical fiber line for multiple times by adopting the OTDR, obtaining OTDR curve data of the optical fiber line, preprocessing the acquired OTDR data for subsequent data analysis, denoising the acquired OTDR data, and obtaining the denoised OTDR curve data, wherein the OTDR curve data preprocessing comprises constructing a fiber breaking event at the tail of the actually measured OTDR raw data as a termination event, and after the artificial termination event is added, the length of the curve data meets the length of the data required by binary wavelet transformation: l ^ sigma 2^ N, N ∈ N.
S2, processing the OTDR curve data obtained in the first step after denoising by adopting wavelet transformation to the preprocessed OTDR curve data or the denoised curve data segment, obtaining optical fiber signal characteristic points, marking the obtained optical fiber signal characteristic points, performing preliminary positioning according to the characteristics of the events on high-frequency coefficients to obtain all events to be determined, and respectively marking the events to be determined as: the high-frequency coefficient is characterized in that the corresponding high-frequency coefficient value is changed from a negative value to a positive value from the starting point to the end point of the reflection event, the negative minimum value is used as the starting point of the reflection event during primary positioning, and the positive maximum value is used as the end point of the reflection event.
S3, calculating a line average consumption threshold, further accurately positioning an event to be determined by adopting a least square method and related parameters, determining whether curve event analysis is finished according to whether a reflection event with accurate positioning failure exists and whether OTDR curve data is subjected to noise reduction processing, using marked data for training an SVM classification model as a training set, using data for verifying prediction precision of the SVM classification model as a verification set, using a DB3 wavelet base wavelet transformation module maximum value method to perform noise reduction on an OTDR curve segment needing noise reduction, replacing curve segment data corresponding to an original OTDR with the noise-reduced curve segment data, using a DB3 wavelet base wavelet transformation module maximum value method to perform noise reduction on the OTDR curve segment needing noise reduction, calculating transmission power, continuously taking N points from the end point of an initial event, using the least square method to obtain a fitting straight line L, wherein the intercept of the straight line L on an optical power X axis is transmission power, obtaining: total line attenuation-the power at the beginning of the end of transmission event.
S4 supervised data for training SVM classification modelLearning to obtain a projection matrix capable of increasing the distinguishing degree of the OTDR data characteristic points; distributing different weights to the characteristic points in the projection matrix to obtain distance measurement, improving a Gaussian radial basis kernel function by using the distance measurement, and establishing an improved SVM classification model, wherein the improved Gaussian radial basis kernel function is as follows:
Figure BDA0003594972000000051
wherein
Figure BDA0003594972000000052
Is a Gaussian radial basis kernel function parameter obtained by a grid search algorithm, xi,xjRepresenting a feature vector, DM(xi,xj) As a measure of distance, DM(xi,xj) The construction process comprises the following steps:
setting the distance measure in projection space to:
Figure BDA0003594972000000053
||L(xi-xj)||2is L (x)i-xj) Is of two norms, [ L (x)i-xj)]TIs L (x)i-xj) Transposing the matrix, squaring the distance and representing it in matrix form, and measuring the distance DM(xi，xj)。
And S5, respectively verifying the trained SVM classification models by using a verification set, selecting the model with the highest prediction precision on the verification set as a final SVM classifier, and recognizing characteristic points of the OTDR data curve by using the SVM classifier to finally recognize the characteristic points of each position of the optical cable.
And S6, calculating the length of the optical fiber line, the total line attenuation and the average line consumption by utilizing the analyzed events.
An algorithm device for improving analysis accuracy based on OTDR comprises a measurement module, a preprocessing module, a high-frequency coefficient module, a classification model module, a verification module and an analysis module.
The measurement module is connected with the preprocessing module, the preprocessing module is connected with the classification model module, the classification model module is connected with the verification module, and the verification module is connected with the analysis module.
When the method is used, discrete stationary wavelet transform is carried out on OTDR data by adopting a Haar wavelet basis, the characteristics of an event on a high-frequency coefficient are utilized, whether denoising is needed or not and a section needing denoising is determined according to the positioning result of an event to be reflected, section denoising is carried out by adopting a wavelet basis DB3 modulus maximum method, the event is analyzed on the section data after denoising by adopting wavelet transform and a least square method again, the classification and identification method of the special points of the optical fiber line of the SVM classifier is used, the OTDR data is analyzed by the method, and each special point in an OTDR curve is analyzed, so that an operator can know each special position of an optical fiber more visually, the test precision of the OTDR is greatly improved, the analysis precision is improved, and the analysis speed is further improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The term "comprising", without further limitation, means that the element so defined is not excluded from the group consisting of additional identical elements in the process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (8)

1. An algorithm and a device for improving analysis accuracy based on OTDR are characterized by comprising the following steps:
s1, measuring the optical fiber line for multiple times by adopting the OTDR, obtaining OTDR curve data of the optical fiber line, preprocessing the OTDR curve data for subsequent data analysis, denoising the obtained OTDR data, and obtaining the denoised OTDR curve data, wherein the OTDR curve data preprocessing comprises constructing a fiber breakage event at the tail of the actually measured OTDR raw data as a termination event, and after the artificial termination event is added, the length of the curve data meets the length of the data required by binary wavelet transformation;
s2, processing the OTDR curve data obtained in the first step after denoising by adopting wavelet transformation to the preprocessed OTDR curve data or the denoised curve data segment, obtaining optical fiber signal characteristic points, marking the obtained optical fiber signal characteristic points, performing preliminary positioning according to the characteristics of the events on high-frequency coefficients to obtain all events to be determined, and respectively marking the events to be determined as: welding points, breaking points, starting ends, tail ends and over-large bending points;
s3, calculating a line average consumption threshold, further accurately positioning an event to be determined by adopting a least square method and related parameters, determining whether curve event analysis is finished or not according to the existence of a reflection event with accurate positioning failure and whether OTDR curve data is subjected to noise reduction processing or not, using marked data for training an SVM classification model as a training set, using data for verifying the prediction precision of the SVM classification model as a verification set, using a DB3 wavelet base wavelet transformation modulus maximum value method to perform noise reduction on an OTDR curve segment needing noise reduction, and replacing curve segment data corresponding to the original OTDR with the noise-reduced curve segment data;
s4, learning the data used for training the SVM classification model in a supervision mode to obtain a projection matrix capable of increasing the distinguishing degree of the OTDR data feature points; distributing different weights to the characteristic points in the projection matrix to obtain distance measure, improving Gaussian radial basis kernel function by using the distance measure, establishing an improved SVM classification model, and obtaining the improved Gaussian radial basis kernel functionComprises the following steps:
Figure FDA0003594971990000011
wherein
Figure FDA0003594971990000012
Is a Gaussian radial basis kernel function parameter obtained by adopting a grid search algorithm, xi,xjRepresenting a feature vector, DM(xi,xj) Is a distance measure, said DM(xi,xj) The construction process comprises the following steps:
setting the distance measure in projection space to:
Figure FDA0003594971990000021
||L(xi-xj)||2is L (x)i-xj) Is of two norms, [ L (x)i-xj)]TIs L (x)i-xj) Transposing the matrix, squaring the distance and representing it in matrix form, and measuring the distance DM(xi，xj)；
S5, respectively verifying the trained SVM classification models by using a verification set, selecting a model with the highest prediction precision on the verification set as a final SVM classifier, and recognizing characteristic points of OTDR data curves and the optical cables at various positions by using the SVM classifier;
and S6, calculating the length of the optical fiber line, the total line attenuation and the line average loss by using the analyzed events.
2. An OTDR based algorithm and device for improving the accuracy of analysis according to claim 1, where: the length of the curve data in the step S1 satisfies the length of the data required for the binary wavelet transform: l ^ sigma 2^ N, N ∈ N.
3. An OTDR based algorithm and device for improving the accuracy of analysis according to claim 1, where: in the high frequency coefficient in step S2, the characteristic of the emission event is that the corresponding high frequency coefficient value changes from a negative value to a positive value from the start point to the end point of the reflection event, and during the initial positioning, the negative minimum value is used as the start point of the reflection event, and the positive maximum value is used as the end point of the reflection event.
4. An OTDR based algorithm and device for improving the accuracy of analysis according to claim 1, where: in step S3, an OTDR curve segment that needs denoising is denoised by using a DB3 wavelet based wavelet transform modulo maximum method.
5. The OTDR based algorithm and apparatus for improving analysis accuracy according to claim 1, wherein: in the step S3, the transmit power is calculated by continuously taking N points from the end point of the start event, and obtaining a fitting straight line L by using a least square method, where an intercept of the straight line L on the optical power X axis is the transmit power, and obtaining: total line attenuation-the power at the beginning of the end of transmission event.
6. An algorithm device for improving analysis accuracy based on OTDR (optical time domain reflectometry) is characterized by comprising a measuring module, a preprocessing module, a high-frequency coefficient module, a classification model module, a verification module and an analysis module.
7. An OTDR-based algorithmic means for improving the accuracy of analysis according to claim 6, wherein: the measurement module is connected with the preprocessing module, and the preprocessing module is connected with the classification model module.
8. An OTDR-based algorithmic means for improving the accuracy of analysis according to claim 6, wherein: the classification model module is connected with a verification module, and the verification module is connected with an analysis module.
CN202210385889.4A 2022-04-13 2022-04-13 Algorithm and device for improving analysis precision based on OTDR Pending CN114679216A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210385889.4A CN114679216A (en) 2022-04-13 2022-04-13 Algorithm and device for improving analysis precision based on OTDR

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210385889.4A CN114679216A (en) 2022-04-13 2022-04-13 Algorithm and device for improving analysis precision based on OTDR

Publications (1)

Publication Number Publication Date
CN114679216A true CN114679216A (en) 2022-06-28

Family

ID=82078666

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210385889.4A Pending CN114679216A (en) 2022-04-13 2022-04-13 Algorithm and device for improving analysis precision based on OTDR

Country Status (1)

Country Link
CN (1) CN114679216A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116996117A (en) * 2023-08-02 2023-11-03 武汉迅稳佳科技有限公司 Line fault detection method and device suitable for communication optical cable

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108229553A (en) * 2017-12-29 2018-06-29 国网吉林省电力有限公司信息通信公司 A kind of OTDR curve datas analysis method
CN109861746A (en) * 2018-12-17 2019-06-07 中博信息技术研究院有限公司 A kind of OTDR curve data analysis method based on wavelet transformation DNR dynamic noise reduction

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108229553A (en) * 2017-12-29 2018-06-29 国网吉林省电力有限公司信息通信公司 A kind of OTDR curve datas analysis method
CN109861746A (en) * 2018-12-17 2019-06-07 中博信息技术研究院有限公司 A kind of OTDR curve data analysis method based on wavelet transformation DNR dynamic noise reduction

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈晓娟;李鑫蕾;王胜达;姜山;: "一种OTDR曲线数据分析方法", 光通信技术, no. 10 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116996117A (en) * 2023-08-02 2023-11-03 武汉迅稳佳科技有限公司 Line fault detection method and device suitable for communication optical cable

Similar Documents

Publication Publication Date Title
CN108229553B (en) OTDR curve data analysis method
CN108593260B (en) Optical cable line fault positioning and detecting method and terminal equipment
CN109949823B (en) DWPT-MFCC and GMM-based in-vehicle abnormal sound identification method
CN113489534A (en) Optical cable abnormity detection method and device
WO2017076189A1 (en) Otdr event analysis algorithm based on difference window and template matching
CN111695452B (en) RBF neural network-based parallel reactor internal aging degree assessment method
CN103235953B (en) A kind of method of optical fiber distributed perturbation sensor pattern recognition
CN114679216A (en) Algorithm and device for improving analysis precision based on OTDR
CN115035913B (en) Sound abnormity detection method
CN116805061B (en) Leakage event judging method based on optical fiber sensing
CN109282837A (en) Bragg grating based on LSTM network interlocks the demodulation method of spectrum
CN111582406A (en) Power equipment state monitoring data clustering method and system
CN117554752A (en) Power cable fault on-line detection system and method
CN112539772B (en) Positioning method of Sagnac distributed optical fiber sensing system based on convolutional neural network integrated learning
CN107782548A (en) One kind is based on to track vehicle parts detecting system
CN116758056A (en) Electrical terminal production defect detection method
CN113670987B (en) Method, device, equipment and storage medium for identifying oil paper insulation aging state
CN116520068A (en) Diagnostic method, device, equipment and storage medium for electric power data
CN111130634A (en) Method and system for identifying loss event in OPGW (optical fiber composite overhead ground wire)
US20220137119A1 (en) Method and Testing Device
CN115575508A (en) Rail transit rail corrugation identification method based on train vibration and sound composite characteristics
CN114742103A (en) City monitoring data processing method and device based on Internet of things and storage medium
CN113642465A (en) Bearing health assessment method based on relational network
CN113049226A (en) OPGW optical cable health degree evaluation method and system based on environmental parameters
CN112114215A (en) Transformer aging evaluation method and system based on error back propagation algorithm

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