CN116633433B - Model-driven OPGW optical cable fault diagnosis and positioning method - Google Patents
Model-driven OPGW optical cable fault diagnosis and positioning method Download PDFInfo
- Publication number
- CN116633433B CN116633433B CN202310538135.2A CN202310538135A CN116633433B CN 116633433 B CN116633433 B CN 116633433B CN 202310538135 A CN202310538135 A CN 202310538135A CN 116633433 B CN116633433 B CN 116633433B
- Authority
- CN
- China
- Prior art keywords
- optical cable
- fault
- model
- opgw
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 217
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003745 diagnosis Methods 0.000 title claims abstract description 42
- 238000000253 optical time-domain reflectometry Methods 0.000 claims abstract description 25
- 238000013145 classification model Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 241000272194 Ciconiiformes Species 0.000 claims description 38
- 239000013307 optical fiber Substances 0.000 claims description 29
- 238000005457 optimization Methods 0.000 claims description 10
- 238000005452 bending Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 7
- 230000004807 localization Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000013434 data augmentation Methods 0.000 claims description 5
- 230000003190 augmentative effect Effects 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 12
- 230000008569 process Effects 0.000 description 17
- 230000006870 function Effects 0.000 description 15
- 239000011159 matrix material Substances 0.000 description 7
- 238000005259 measurement Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000000835 fiber Substances 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000003416 augmentation Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000007526 fusion splicing Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/079—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
- H04B10/0791—Fault location on the transmission path
-
- 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]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
Abstract
The invention discloses a model-driven OPGW optical cable fault diagnosis and positioning method, which relates to the technical field of power equipment detection and comprises the following steps: acquiring optical cable data and fault point distances and detection curves acquired through OTDR when line faults occur; preprocessing the detection curve and the optical cable data, training the preprocessed data to obtain an optimal optical cable fault classification model, and classifying optical cable faults; constructing a T-S fuzzy fault tree optical cable fault diagnosis model to diagnose the cause of the optical cable fault; and constructing an optical cable fault positioning model, and performing fault positioning based on the fault point distance. The invention realizes the accurate classification of the fault types of the optical cable, realizes the accurate positioning of the fault points of the optical cable by utilizing an optical cable positioning algorithm, utilizes the T-S fuzzy fault tree to infer and analyze the faults of the optical cable, can know the cause of the faults most likely to be caused by the reasoning result, is convenient for staff to accurately apply, and adopts proper measures to reduce the occurrence times of the faults.
Description
Technical Field
The invention relates to the technical field of power equipment detection, in particular to an OPGW optical cable fault diagnosis and positioning method based on model driving.
Background
The optical fiber composite overhead ground wire (Optical Fiber Composite Overhead Ground Wire, OPGW) is a cable containing communication optical fibers inside. The system has the functions of ground wire and communication, is an important infrastructure for the safe operation of a physical carrier and a power grid of an electric power communication network, and plays a vital role in an electric power system. With the overall construction of smart power grids, power grid production and operation business are growing day by day, and OPGW optical cables are exposed in the field for a long time and are easily affected by complex weather such as strong wind and temperature to break and other faults due to the unique erection mode, and in some special geographic environments, for example: it is difficult to locate the fault geographical location in areas such as rivers, steep slopes, etc. Once the power optical cable line fails, the optical cable communication network is interrupted for a long time, so that a large amount of optical cable communication network data is lost, great economic loss is brought to users, and the safe operation of a power grid is seriously affected. Therefore, the fault diagnosis and positioning of the OPGW optical cable are significant in guaranteeing safe and reliable operation of the power optical fiber communication private network.
Currently, the main method for detecting the fault of the OPGW optical cable is to obtain the relevant fault point of the optical fiber and obtain the distance of the fault point by using the OTDR and the test curve and event point information obtained by the OTDR measurement, and the staff searches along the line to finally find the position of the fault point and overhaul the fault point to remove the fault. Although the method can find the fault point of the optical fiber, the problems of tail fiber, jump fiber, coiling fiber and the like exist because the actual optical cable wiring is complex, the actual geographic position of the fault point can not be accurately positioned only by the optical fiber distance measured by the OTDR, and a great deal of manpower and time are required to find the actual position of the fault point. Meanwhile, the characteristics of the OTDR signal profile may be divided into a start event, a reflection event, a non-reflection event, and an end event, wherein the fault event mainly occurs in the reflection event and the non-reflection event. The reflection event is caused by the fact that the mechanical joint is not firmly connected, the optical fiber is broken, and the like. Common non-reflective event causes are fusion splicing, bending, aging, etc. The method only obtains the type of the event point, lacks accurate analysis of the type of the fault, and does not diagnose the cause of the fault by fusing the state of the optical cable.
Therefore, the method for diagnosing and positioning the OPGW optical cable faults based on model driving is provided, and the problem to be solved by the person skilled in the art is urgent.
Disclosure of Invention
In view of the above, the invention provides a model-driven OPGW optical cable fault diagnosis and positioning method, which accurately analyzes the fault type, fuses the optical cable state to perform fault diagnosis and positioning on the cause of the fault, and adopts the following technical scheme to realize the purposes:
the model-driven OPGW optical cable fault diagnosis and positioning method comprises the following steps:
acquiring OPGW optical cable data and a fault point distance and a detection curve which are acquired through OTDR when line faults occur;
preprocessing the detection curve and OPGW optical cable data, training the preprocessed data to obtain an optimal optical cable fault classification model, and classifying OPGW optical cable faults;
constructing a T-S fuzzy fault tree optical cable fault diagnosis model to diagnose the fault cause of the OPGW optical cable;
and constructing an optical cable fault positioning model, and performing fault positioning based on the fault point distance.
Optionally, the OPGW cable data includes: OPGW optical cable line trend map, optical cable splice box position point, optical cable inflection point, special geographic position longitude and latitude coordinates and meteorological data, distributed optical fiber sensing data and OPGW optical cable record.
Optionally, the specific steps of the pretreatment are as follows:
registering an optical cable path trend map by adopting a standard coordinate system, registering an optical cable line according to longitude and latitude coordinates at a special geographic position, and generating optical cable line data;
performing data augmentation on the distributed optical fiber sensing data to obtain augmented data;
and carrying out normalized denoising treatment on the signal curves of the OTDR fusion point, the breaking point and the bending oversized point, and carrying out feature extraction.
Optionally, the training optical cable fault classification model includes: based on the preprocessed data, training an extreme learning machine recognition model, searching a global optimal value by utilizing a pelican optimization algorithm, optimizing the hidden layer weight and deviation of the extreme learning machine recognition model, and obtaining an optimal optical cable fault classification model to classify the optical cable fault types.
Optionally, the specific steps of obtaining the optimal optical cable fault classification model are as follows:
s11: initializing the number of population members, the maximum iteration number and the space dimension;
s12: moving pelicans to the prey, wherein the updating of the pelican optimization algorithm is divided into two stages, the first stage is an exploration stage, and the second stage is a exploitation stage, and the positions of the pelicans are respectively updated;
s13: calculating individual fitness according to the updated positions of the pelicans, updating the current object parameters into optimal candidate schemes, and circulating S12-S13 to judge whether the maximum iteration times are reached; and if the maximum iteration number is reached, outputting an optimal solution of the hidden layer weight and the deviation, and optimizing the recognition model of the extreme learning machine.
Optionally, the constructing the T-S fuzzy fault tree optical cable fault diagnosis model includes:
and constructing a T-S fuzzy fault tree model by combining the T-S model and a fuzzy theory, quantitatively calculating by using the T-S fuzzy fault tree model, and optimizing the traditional fault tree analysis method to realize the diagnosis of the optical cable faults.
Optionally, the specific steps of diagnosing the fault of the optical fiber are as follows:
s21: acquiring factors which cause the OPGW optical cable to fail, and establishing a T-S fuzzy fault tree model according to the factors;
s22: determining a T-S fuzzy fault tree gate rule according to expert experience and/or historical fault data;
s23: and analyzing the T-S fuzzy fault tree to obtain fuzzy possibility of the faults of the optical cable caused by each event.
Optionally, the building the optical cable fault location model includes:
s31: generating a path according to the actual trend of the optical cable, and marking the path to obtain an optical cable line linear reference system;
s32: when the optical cable fails, the OTDR is utilized to obtain the distance of the fault point, the distance of the fault point is converted into the distance of the optical cable, and the longitude and latitude coordinates of the fault point are obtained by utilizing a positioning algorithm and displayed in a linear reference system.
Compared with the prior art, the invention discloses and provides the OPGW optical cable fault diagnosis and positioning method based on model driving, which has the following beneficial effects:
the invention solves the problem that the existing OPGW optical cable fault detection technology cannot classify and locate the fault type, realizes the accurate classification of the optical cable fault type by using the POA-ELM algorithm, realizes the accurate location of the optical cable fault point by using the optical cable location algorithm, and can lead staff to directly and quickly reach the fault point to carry out maintenance operation, thereby saving a great amount of labor cost and reducing economic loss;
the invention utilizes the T-S fuzzy fault tree to infer and analyze the cause of the optical fault, and the cause of the fault is most likely to be caused by the cause of the optical fault can be known through the inference result, thereby being convenient for staff to accurately plan and adopting proper measures to reduce the occurrence times of the fault;
the invention not only can effectively carry out fault diagnosis and positioning on the current OPGW optical cable line, but also can be used for fault diagnosis and positioning of other OPGW lines based on the model, thereby providing effective technical support for ensuring safe and reliable operation of the OPGW optical cable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a model-driven OPGW optical cable fault diagnosis and positioning method provided by the invention;
FIG. 2 is a flow chart of a POA-ELM combination algorithm for accurately classifying optical cable faults;
FIG. 3 is a flow chart of optical cable fault reasoning based on a T-S fuzzy fault tree provided by the invention;
FIG. 4 is a diagram of a T-S fuzzy fault tree structure provided by the invention;
FIG. 5 is a schematic diagram of the establishment process of a linear reference system in the OPGW optical cable fault accurate positioning method provided by the invention;
FIG. 6 is a flowchart of an OPGW optical cable fault accurate positioning algorithm provided by the invention;
fig. 7 is a flowchart of an overall fault diagnosis and positioning method for an OPGW optical cable based on model driving.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
The embodiment of the invention discloses a model-driven OPGW optical cable fault diagnosis and positioning method, which is shown in figure 1 and comprises the following steps:
acquiring OPGW optical cable data and a fault point distance and a detection curve which are acquired through OTDR when line faults occur;
preprocessing the detection curve and OPGW optical cable data, training the preprocessed data to obtain an optimal optical cable fault classification model, and classifying OPGW optical cable faults;
constructing a T-S fuzzy fault tree optical cable fault diagnosis model to diagnose the fault cause of the OPGW optical cable;
and constructing an optical cable fault positioning model, and performing fault positioning based on the fault point distance.
Further, the OPGW cable data includes: OPGW optical cable line trend map, optical cable splice box position point, optical cable inflection point, special geographic position longitude and latitude coordinates and meteorological data, distributed optical fiber sensing data and OPGW optical cable record.
Further, the specific steps of the pretreatment are as follows:
registering an optical cable path trend map by adopting a standard coordinate system, registering an optical cable line according to longitude and latitude coordinates at a special geographic position, and generating optical cable line data;
performing data augmentation on the distributed optical fiber sensing data to obtain augmented data;
and carrying out normalized denoising treatment on the signal curves of the OTDR fusion point, the breaking point and the bending oversized point, and carrying out feature extraction.
Further, the training optical cable fault classification model includes: based on the preprocessed data, training an extreme learning machine recognition model, searching a global optimal value by utilizing a pelican optimization algorithm, optimizing the hidden layer weight and deviation of the extreme learning machine recognition model, and obtaining an optimal optical cable fault classification model to classify the optical cable fault types.
Further, the specific steps of obtaining the optimal optical cable fault classification model are as follows:
s11: initializing the number of population members, the maximum iteration number and the space dimension;
s12: moving pelicans to the prey, wherein the updating of the pelican optimization algorithm is divided into two stages, the first stage is an exploration stage, and the second stage is a exploitation stage, and the positions of the pelicans are respectively updated;
s13: calculating individual fitness according to the updated positions of the pelicans, updating the current object parameters into optimal candidate schemes, and circulating S12-S13 to judge whether the maximum iteration times are reached; and if the maximum iteration number is reached, outputting an optimal solution of the hidden layer weight and the deviation, and optimizing the recognition model of the extreme learning machine.
Further, the constructing the T-S fuzzy fault tree optical cable fault diagnosis model comprises the following steps:
and constructing a T-S fuzzy fault tree model by combining the T-S model and a fuzzy theory, quantitatively calculating by using the T-S fuzzy fault tree model, and optimizing the traditional fault tree analysis method to realize the diagnosis of the optical cable faults.
Further, the specific steps of the diagnosis of the optical fiber faults are as follows:
s21: acquiring factors which cause the OPGW optical cable to fail, and establishing a T-S fuzzy fault tree model according to the factors;
s22: determining a T-S fuzzy fault tree gate rule according to expert experience and/or historical fault data;
s23: and analyzing the T-S fuzzy fault tree to obtain fuzzy possibility of the faults of the optical cable caused by each event.
Further, the constructing the optical cable fault location model includes:
s31: generating a path according to the actual trend of the optical cable, and marking the path to obtain an optical cable line linear reference system;
s32: when the optical cable fails, the OTDR is utilized to obtain the distance of the fault point, the distance of the fault point is converted into the distance of the optical cable, and the longitude and latitude coordinates of the fault point are obtained by utilizing a positioning algorithm and displayed in a linear reference system.
In embodiment 1, an OPGW optical cable operation fault diagnosis and positioning method specifically includes:
step 1, data acquisition;
acquiring an OPGW optical cable line trend map; the position points of the optical cable joint box, the inflection points of the optical cable, the longitude and latitude coordinates of special geographic positions such as the set points of the OPGW rod tower and the like and meteorological data; distributed optical fiber sensing data, OPGW optical cable installation, maintenance, fault recording and the like; and collecting signal curves of the OTDR fusion point, the breaking point and the bending oversized point, and obtaining the fault point distance.
Step 2, data preprocessing;
registering an optical cable path trend map by adopting a standard coordinate system, registering an optical cable line according to longitude and latitude coordinates at a special geographic position, and generating optical cable line data; performing data augmentation on the distributed optical fiber sensing data to obtain augmented data; and (3) firstly carrying out normalization denoising treatment on the signal curves of the fusion point, the breaking point and the oversized bending point, and then carrying out feature extraction.
Step 3, constructing a POA-ELM optical cable fault classification model;
constructing a POA-ELM optical cable fault classification model, taking the data extracted by the features in the second step as the input of a training extreme learning machine (ELM, extreme Learning Machines) recognition model, searching a global optimal value by utilizing a pel optimization algorithm (POA, pelican Optimization Algorithm), and optimizing a hidden layer weight omega and a deviation b of the ELM recognition model to realize classification of optical cable fault types;
the specific process for constructing the POA-ELM optical cable fault classification model comprises the following steps:
step 3-1, initializing the number N of population members, the maximum iteration number T and the space dimension m;
step 3-2, the pelican moves towards the prey, the updating of the pelican optimizing algorithm is divided into two stages, the first stage is an exploration stage, the second stage is a exploitation stage, and the positions of the pelican are respectively updated;
step 3-3, calculating individual fitness according to the updated position of the pelicans, updating the current object parameters into an optimal candidate scheme, and judging whether the maximum iteration times are reached; if the maximum iteration times are reached, outputting an optimal solution of the hidden layer weight omega and the deviation b for optimizing the ELM recognition model; otherwise, updating all population members according to the first stage and the second stage, and transferring to the step 3-2;
step 4, constructing a T-S fuzzy fault tree optical cable fault diagnosis model;
the invention combines the T-S model with the fuzzy theory for modeling, and utilizes the advantage that the T-S model can quantitatively calculate, optimizes the traditional fault tree analysis method, and realizes the diagnosis of the optical cable faults;
the specific process for constructing the T-S fuzzy fault tree optical cable fault diagnosis model is as follows:
step 4-1, summarizing factors possibly causing the OPGW optical cable to fail, and establishing a T-S fuzzy fault tree model according to the factors;
step 4-2, determining a T-S fuzzy fault tree gate rule according to expert experience and historical fault data;
step 4-3, analyzing the T-S fuzzy fault tree to obtain fuzzy possibility that each event possibly causes the fault of the optical cable;
step 5, constructing an OPGW optical cable fault positioning model;
the OPGW optical cable is complex in actual wiring, the actual geographic position of the fault point cannot be accurately positioned only by using the fault point distance obtained by OTDR measurement, and an OPGW optical cable fault positioning model needs to be established to realize rapid and accurate positioning of the fault point;
the specific process for constructing the OPGW optical cable fault positioning model is as follows:
step 5-1, generating a path according to the actual trend of the optical cable, and marking the path to obtain an optical cable line linear reference system;
and 5-2, when the optical cable fails, obtaining a fault point distance by using an OTDR, converting the fault point distance into the optical cable distance by using a formula, obtaining longitude and latitude coordinates of the fault point by using a positioning algorithm, and displaying the longitude and latitude coordinates in a linear reference system.
In embodiment 2, a model-driven OPGW-based optical cable fault diagnosis and localization method includes the steps of:
step 1: obtaining data;
acquiring special geographic position longitude and latitude coordinates such as an OPGW optical cable line trend map, an on-site measurement optical cable joint box position, an optical cable inflection point, an OPGW tower set point and the like, storing the special geographic position longitude and latitude coordinates into a GIS database, and generating an OPGW optical cable line linear reference system for positioning an optical cable fault position through the data; acquiring meteorological data of an OPGW shaft tower set area by using an API interface with open weather, wherein the meteorological data comprises temperature, relative humidity, wind direction, wind speed, air quality and precipitation; acquiring distributed optical fiber sensing data, wherein the distributed optical fiber sensing data comprises OPGW optical cable temperature, strain and vibration data, and acquiring OPGW optical cable installation records, maintenance records, fault records and the like, and diagnosing the fault cause of the optical fiber through the data; and collecting signal curves of the OTDR fusion point, the fracture point and the bending oversize point, and classifying the fault types of the optical cable.
Step 2: preprocessing data;
registering an optical cable path trend map by adopting a standard coordinate system, registering an optical cable line according to longitude and latitude coordinates at a special geographic position, and generating optical cable line data; data augmentation is carried out on the distributed optical fiber sensing data to obtain augmentation data, wherein the augmentation data comprises temperature variation, strain variation, vibration amplitude, vibration frequency, strain and temperature, and the temperature variation is calculated as T=T h -T c T is the temperature variation, T h To obtain the ambient temperature, T c A temperature measured for the distributed optical fiber sensing device; the strain change was calculated as mu ε ＝μ εa -μ εb Wherein μ is ε Mu, the strain change εa The strain of OPGW optical cable in calm and no abnormal state is calibrated, mu εb The strain value obtained by the distributed optical fiber sensing equipment is measured; vibration amplitude, strain quantity and temperature are distributed optical fiberThe actual measured data of the sensing equipment are obtained through amplitude-frequency conversion of the vibration amplitude; because various complex information can be contained in the acquired data information of the fusion point, the fracture point and the overlarge bending point, the signal is standardized, and the influence of the difference of the data on the characteristic extraction process can be prevented. Taking the characteristics of the acquired signal curve into consideration, a min-max mode is selected for normalization processing, and the method is defined as follows:
wherein x is norm Is normalized data, x i Is the original data, max (x), min (x) are the maximum value and minimum value in the original data, respectively.
And after the data is normalized, denoising the data by adopting an adaptive filtering algorithm. The self-adaptive filter is an optimal filtering method developed on the basis of linear filtering such as wiener filtering and Kalman filtering, has the advantages of simple structure, small calculated amount, strong robustness and easiness in implementation, and can adjust the weight of the filter according to the state and environmental change of the self-adaptive filter, so that the purpose of removing noise and restoring real data is realized. And extracting the characteristics of 5 characteristics of short-time zero-crossing rate, average value, short-time energy, variance and root mean square of the normalized and denoised data information to obtain a characteristic vector as input for training the ELM recognition model.
Step 3: constructing a POA-ELM optical cable fault classification model;
and (3) constructing a POA-ELM optical cable fault classification model, taking the data after feature extraction in the step (2) as input of a training extreme learning machine recognition model, searching a global optimal value by utilizing a pelican optimization algorithm, and optimizing a hidden layer weight omega and a deviation b of the ELM recognition model to realize classification of optical cable fault types.
As shown in fig. 2, a flow of a POA-ELM combination algorithm for accurately classifying optical cable faults includes:
firstly, an ELM recognition model is established, and the specific steps are as follows:
the ELM comprises an input layer, a hidden layer and an output layerThe neurons between the hidden layer and the output layer are fully connected. In a classification problem with N sample training to distinguish m categories, a given training set { x }, is assumed i ,t i |x i ∈R D ,t i ∈R m I=1, 2,.. i Representing the ith data example, t i Representing the label corresponding to the ith data example, D represents the D arbitrary different samples of the input layer, and the set R represents all training data, then the output h of the hidden layer j (x)：
h j (x)＝G(ω j ,b j ,x i )＝G(ω j x i +b j ) (1)
Wherein omega is j And b j And respectively representing the weight and the deviation of the j-th hidden layer node, wherein G represents the activation function of the neural network, and the Sigmoid function is selected as the activation function. An extreme learning machine with L hidden layer nodes is represented as follows:
wherein beta is j Representing a weight vector connecting a j-th hidden layer node to an output layer node, the above equation can be expressed in a matrix as:
Hβ＝T (3)
wherein H is a hidden layer output matrix, beta is an output weight matrix, and T is a desired output matrix.
Wherein a is the weight from the input layer to the hidden layer, b is the deviation,
in equation (3), only β is unknown, and is obtained by searching for the least-norm least-squares solution of the linear model:
in the method, in the process of the invention,represents the Moore-Penrose generalized inverse of the hidden layer output matrix H.
According to the above description, the hidden layer weights ω and the bias b of the ELM recognition model are randomly generated, and in order to obtain a better classification result, the hidden layer weights ω and the bias b of the ELM are optimized by using the stronger global searching capability of the POA, so that the final classification effect of the algorithm achieves a faster solving capability and a higher accurate effect.
The specific steps of constructing the POA-ELM optical cable fault classification model are as follows:
initializing a population
The initialization of the number of population members N, the maximum number of iterations T, and the spatial dimension m, the initialization of the pelican population can be expressed as follows:
x i,j ＝l j +rand(u j -l j ),i＝1,2,...,N,j＝1,2,...,m (7)
wherein x is i,j For the position of the ith dimension of the i-th pelican, N is the population number of the pelican, m is the dimension for solving the problem, and rand is [0,1]Random numbers within a range, u j Is the upper boundary of the j-th dimension of the solution problem, l j Is the lower boundary of the j-th dimension of the solution problem. The pelican population may be represented by the following matrix:
wherein X is the population matrix of the pelicans, X i Is the position of the i-th pelican.
(II) calculating an objective function
In the pelican optimization algorithm, an objective function for solving the problem can be used to calculate an objective function value of the pelican; the objective function value of the pelican population may be represented by an objective function value vector:
wherein F is the objective function vector of the population of pelars, F i Is the objective function value of the ith pelican.
(III) first stage (exploration stage)
In the first stage, the pelicans locates the prey and then moves to this defined area. At this stage, the POA algorithm may scan the search space, exploiting the exploration capabilities of the POA algorithm in different areas of the search space. The expression can be expressed as follows:
in the method, in the process of the invention,for the j-th dimension of the i-th pelican based on the first phase updated position, rand is 0,1]Random numbers in the range, I is a random integer of 1 or 2, p j Is the j-th dimension position of the prey, F p Is the objective function value of the prey. If the objective function value is improved at this location, then a new location of the pelicans is accepted, and this update process is also called an active update, which can be described by the following formula:
in the method, in the process of the invention,is the new position of the i-th pelican,/>Is based on the objective function value of the first stage.
(IV) second stage (development stage)
In the second phase, after the pelicans reach the water surface, they spread the wings on the water surface, which action may cause them to catch more fish in the attacked area. At this stage, the POA algorithm can converge to a better location. The expression can be expressed as follows:
in the method, in the process of the invention,for the j-th dimension of the position based on the second phase updated i-th pelican, rand is [0,1 ]]The random number in the range, R is a random integer of 0 or 2, T is the current iteration number, and T is the maximum iteration number. At this stage, the effective update is described by the following formula:
in the method, in the process of the invention,is the new position of the i-th pelican,/>Is based on the objective function value of the second stage.
(fifth) judgment
After all population members are updated in two stages, the optimal solution up to now is updated, and then whether the algorithm reaches a termination condition is judged; and if the end condition is reached, outputting the optimal solution of the hidden layer weight omega and the deviation b, and ending the iterative process, otherwise, repeating the steps based on the formula 9-the formula 12 until the complete execution is ended. And finally, inputting the optimal solution obtained in the algorithm iteration process into the ELM recognition model.
Step 4: constructing a T-S fuzzy fault tree optical cable fault diagnosis model;
the invention combines the T-S model with the fuzzy theory for modeling, and utilizes the advantage that the T-S model can quantitatively calculate, optimizes the traditional fault tree analysis method, and realizes the diagnosis of the optical cable faults;
as shown in fig. 3, the cable fault diagnosis includes:
s41: summarizing factors possibly causing the OPGW optical cable to generate faults, and establishing a T-S fuzzy fault tree model according to the factors;
in the invention, an optical cable fault is taken as a top event, optical cable fault types are classified in the step 3, three fault types are taken as intermediate events, and factors possibly causing the intermediate events are analyzed as bottom events according to optical cable fault records and maintenance records, so that an OPGW optical cable fault T-S fuzzy fault tree structure is established as shown in figure 4, and an OPGW optical cable fault T-S fuzzy fault tree event code is shown in table 1;
TABLE 1
S42: determining a T-S fuzzy fault tree gate rule according to expert experience and historical fault data;
assuming that the fault degree of each event is divided into normal, slight fault and serious fault, which are respectively represented by 0, 0.5 and 1, a T-S fuzzy gate rule table is obtained according to expert experience and historical fault data, each row in the rule table represents a fuzzy rule, and as shown in table 2, the rule represented by the first row is: when the strain amount of the basic event is normal, the vibration amplitude is normal, the vibration frequency is normal and the wind speed is normal, the possibility that the middle event is not bent too much is 1. The third row represents the rule: when the strain amount of the basic event is normal, the vibration amplitude is normal, the vibration frequency is normal and the wind speed is very high, the possibility that the middle event does not bend too much is 0.6, the possibility that the middle event bends slightly too much is 0.3, and the possibility that the middle event bends too much is 0.1. And so on, the remaining T-S fuzzy gate corresponding rules may be set.
TABLE 2
S43: analyzing the T-S fuzzy fault tree to obtain fuzzy possibility that each event possibly causes the fault of the optical cable;
the invention adopts an expert investigation method to obtain the fuzzy probability of the basic event, and utilizes an analytic hierarchy process to measure the expert weight to obtain the proportion k occupied by different experts in the evaluation process, and the expert r evaluates the basic event X according to experience and the running state of the optical cable j Probability interval L rj ,R rj ]Obtaining the median value of the interval as S rj ＝(L rj +R rj ) 2, and evaluate the weight k in combination therewith r The expert can be obtained for the basic event X j Is of the blur probability P of (2) rj ：
P rj ＝k r [L rj ,S rj ,R rj ] (14)
Thus, basic event X j Is of the blur probability P of (2) j The method comprises the following steps:
in the T-S gate rule l (l=1, 2, …, m), a fuzzy tree (x 11 ,x 12 ,...,x 1μ1 ),(x 21 ,x 22 ,...,x 2μ2 )...(x n1 ,x n2 ,…,x nμn ) And (y) 1 ,y 2 ,…,y k ) Respectively represent basic event x= (X) 1 ,X 2 ,…,X n ) And the fault degree of the upper event, when the fuzzy probability of the fault degree corresponding to the basic event is thatOutput event y i Is p l (y i )，i 1 ＝1,2,…,μ 1 ；i 2 ＝1,2,…,μ 2 ；i n ＝1,2,…,μ n The method comprises the steps of carrying out a first treatment on the surface of the i=1, 2, …, n. Possibility of execution of rule l +.>The method comprises the following steps:
thus, the fuzzy probability of the upper event can be obtained as follows:
if the failure degree of the basic event X '= (X' 1 ,x′ 2 ,…,x′ n ) The failure probability of the upper event is:
in the method, in the process of the invention,when the gate rule is l, membership of the T-S fuzzy fault tree corresponding to the basic event; x'. j As basic event X j Is a fault level of (a); />For X 'in rule I' j Membership to fuzzy sets.
Therefore, when the fuzzy probability and the fault degree of the basic event are known, the fuzzy probability of the related intermediate event is calculated through the formula 16-the formula 19, the respective fuzzy probability corresponding to various fault degrees of the top-level event can be deduced from the intermediate event, the fault occurrence condition is known, and the fault reason can be analyzed from top to bottom.
Step 5: constructing an OPGW optical cable fault positioning model;
the OPGW optical cable is complex in actual wiring, the actual geographic position of the fault point cannot be accurately positioned only by using the fault point distance obtained by OTDR measurement, and an OPGW optical cable fault positioning model needs to be established to realize rapid and accurate positioning of the fault point;
the specific process for constructing the OPGW optical cable fault positioning model is as follows:
s51: generating a path according to the actual trend of the optical cable, marking the path to obtain an optical cable line linear reference system, and establishing the optical cable line linear reference system, wherein the specific process is as shown in fig. 5:
carrying out standard coordinate system registration operation on the obtained optical cable line trend map, and registering the optical cable line according to longitude and latitude coordinates of reference points (buildings, sites, inflection points, joint boxes and the like) along the line measured in the field to generate optical cable line data;
converting the optical cable line data in the first step into a path by using ARCGIS software;
marking the path generated in the step (II), wherein the specific operation is as follows:
(1) Initializing all points in a path by using a linear reference tool in ARCGIS, so that each point in an optical cable line has a reference distance corresponding to an initial point in the linear reference system, and combining an optical cable maintenance record and an optical cable maintenance record, so that part of points have practical significance in the reference system;
(2) Marking the reference point data in the optical cable line trend map obtained in the step 1 into the optical cable linear reference system;
(3) And marking special geographical position points such as the position points of the optical cable joint box and the inflection points of the optical cable in the optical cable line, and taking the accurate positioning of the follow-up faults as a reference.
S52: when an optical cable fails, obtaining a fault point distance by using an OTDR, converting the fault point distance into the optical cable distance by using a formula, obtaining longitude and latitude coordinates of the fault point by using a positioning algorithm, and displaying the longitude and latitude coordinates in a linear reference system;
the optical fiber distance between the fault point and the detection point of the optical cable can be converted into the actual distance of the optical cable by using the formula and is recorded as S T . The specific process is as follows:
(1) Obtaining the optical fiber distance s of the fault point from the measuring point by using OTDR, repeating the operation for five times, and recording as an array { s };
(2) Averaging the distance array { s }, recorded asWherein S is 1 -S 5 The distance between the optical fiber fault point and the measuring point obtained in the time of OTDR five times measurement is respectively, and the optical fiber distance is required to be converted into an optical cable distance;
(3) According to the twisting shrinkage rate P of the optical cable r Optical cable bending degree C r Using the formulaObtaining the optical cable distance from the measuring point to the fault point, wherein S T The converted optical cable distance is obtained.
(II) the actual distance S of the optical cable T The method is converted into an actual geographic position, and is converted into a point event in a linear reference system, the point event is displayed on the GIS map, the accurate positioning of a fault point is realized, a specific process is shown in fig. 6, an OPGW optical cable fault accurate positioning algorithm, and the accurate positioning of the fault point is realized, and the method comprises the following steps:
(1) Inquiring data in the GIS database, and measuring the distance S of the optical cable T Distance L from each special point in the database to the measurement point n Subtracting to obtain a difference S T -L n Taking the absolute value of the difference and taking the absolute value to minimize min (|S) T -L n I), get distance S from the power cable T A nearest reference point, obtaining a value of n that minimizes the value;
(2) If |S T -L n I > 0, determining cable distance S T Between the position point numbers n and n+1, the longitude and latitude coordinates (x n ,y n )，(x n+1 ,y n+1 ) Both of theseDistance L of point from measurement point n And L is equal to n+1 By the formulaThe coordinates of the fault point can be calculated, wherein (x) F ,y F ) Zeta is longitude and latitude coordinates of fault point i The cable length is reserved for the ith splice enclosure.
(3) If |S T -L n I < 0, determining the cable distance S T Between position point numbers n-1 and n, by the formulaLongitude and latitude coordinates of the fault point can be calculated.
(III) if |S T -L n The longitude and latitude coordinates of the point are the coordinates of the fault point;
and (IV) calculating longitude and latitude coordinates, and displaying the point on the GIS map in the step S51.
In embodiment 3, as shown in fig. 7, an overall flow chart of an OPGW optical cable fault diagnosis and positioning method based on model driving includes:
and installing an OTDR at the tail end of the optical cable line, obtaining a fault point distance and a detection curve by using the OTDR when the line is in fault, inputting the OTDR detection curve into a POA-ELM classification model, diagnosing a fault cause by using a T-S fuzzy fault tree, inputting the fault point distance into an OPGW optical cable fault positioning model, obtaining a fault type, a cause of the fault and longitude and latitude coordinates of a fault point, and realizing the fault diagnosis and positioning of the OPGW optical cable.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The model-driven OPGW optical cable fault diagnosis and positioning method is characterized by comprising the following steps of:
acquiring optical fiber composite overhead ground wire OPGW optical cable data and a fault point distance and a signal curve acquired through OTDR when line faults occur;
preprocessing the signal curve and OPGW optical cable data, training the preprocessed data to obtain an optimal optical cable fault classification model, and classifying OPGW optical cable faults;
the training to obtain the optimal optical cable fault classification model comprises the following steps: based on the preprocessed data, training an extreme learning machine recognition model, searching a global optimal value by utilizing a pelican optimization algorithm, and optimizing the hidden layer weight and deviation of the extreme learning machine recognition model to obtain an optimal optical cable fault classification model for classifying the optical cable fault types;
the specific steps for obtaining the optimal optical cable fault classification model are as follows:
s11: initializing the number of population members, the maximum iteration number and the space dimension;
s12: moving pelicans to the prey, wherein the updating of the pelican optimization algorithm is divided into two stages, the first stage is an exploration stage, and the second stage is a exploitation stage, and the positions of the pelicans are respectively updated;
s13: calculating individual fitness according to the updated positions of the pelicans, updating the current object parameters into optimal candidate schemes, and circulating S12-S13 to judge whether the maximum iteration times are reached; if the maximum iteration times are reached, outputting an optimal solution of the hidden layer weight and the deviation, and optimizing an extreme learning machine recognition model;
constructing a T-S fuzzy fault tree optical cable fault diagnosis model to diagnose the fault cause of the OPGW optical cable;
and constructing an optical cable fault positioning model, and performing fault positioning based on the fault point distance.
2. The model driven OPGW cable fault diagnosis and localization method of claim 1, wherein the OPGW cable data comprises: OPGW optical cable line trend map, optical cable splice box position point, optical cable inflection point, special geographic position longitude and latitude coordinates and meteorological data, distributed optical fiber sensing data and OPGW optical cable record.
3. The model-driven OPGW optical cable fault diagnosis and localization method according to claim 2, wherein the specific steps of the preprocessing are:
registering an optical cable path trend map by adopting a standard coordinate system, registering an optical cable line according to longitude and latitude coordinates at a special geographic position, and generating optical cable line data;
performing data augmentation on the distributed optical fiber sensing data to obtain augmented data;
and carrying out normalized denoising treatment on the signal curves of the OTDR fusion point, the breaking point and the bending oversized point, and carrying out feature extraction.
4. The model-driven OPGW optical cable fault diagnosis and localization method of claim 1, wherein constructing a T-S fuzzy fault tree optical cable fault diagnosis model comprises:
and constructing a T-S fuzzy fault tree model by combining the T-S model and a fuzzy theory, quantitatively calculating by using the T-S fuzzy fault tree model, and optimizing the traditional fault tree analysis method to realize the diagnosis of the optical cable faults.
5. The model driven OPGW optical cable fault diagnosis and localization method according to claim 4, wherein the specific steps of the diagnosis of the optical cable fault are:
s21: acquiring factors which cause the OPGW optical cable to fail, and establishing a T-S fuzzy fault tree model according to the factors;
s22: determining a T-S fuzzy fault tree gate rule according to expert experience and/or historical fault data;
s23: and analyzing the T-S fuzzy fault tree to obtain fuzzy possibility of the faults of the optical cable caused by each event.
6. The model driven OPGW-based cable fault diagnosis and localization method of claim 1, wherein the constructing the cable fault localization model comprises:
s31: generating a path according to the actual trend of the optical cable, and marking the path to obtain an optical cable line linear reference system;
s32: when the optical cable fails, the OTDR is utilized to obtain the distance of the fault point, the distance of the fault point is converted into the distance of the optical cable, and the longitude and latitude coordinates of the fault point are obtained by utilizing a positioning algorithm and displayed in a linear reference system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310538135.2A CN116633433B (en) | 2023-05-12 | 2023-05-12 | Model-driven OPGW optical cable fault diagnosis and positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310538135.2A CN116633433B (en) | 2023-05-12 | 2023-05-12 | Model-driven OPGW optical cable fault diagnosis and positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116633433A CN116633433A (en) | 2023-08-22 |
| CN116633433B true CN116633433B (en) | 2024-03-08 |
Family
ID=87641022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310538135.2A Active CN116633433B (en) | 2023-05-12 | 2023-05-12 | Model-driven OPGW optical cable fault diagnosis and positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116633433B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118376408A (en) * | 2024-06-25 | 2024-07-23 | 沈阳顺义科技股份有限公司 | Rolling bearing vibration fault diagnosis method, device, medium and product |
| CN118534256B (en) * | 2024-07-19 | 2024-09-17 | 鄂尔多斯市泛胜数据技术有限公司 | Power line fault detection and positioning method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107917734A (en) * | 2017-11-29 | 2018-04-17 | 国网吉林省电力有限公司信息通信公司 | Cable's Fault Forecasting Methodology based on temperature and resistance |
| CN109474333A (en) * | 2018-12-27 | 2019-03-15 | 国网山西省电力公司晋中供电公司 | A kind of electric power optical cable real-time monitoring protection system based on deep learning |
| CN115098687A (en) * | 2022-07-18 | 2022-09-23 | 国家电网有限公司信息通信分公司 | Alarm checking method and device for scheduling operation of electric power SDH optical transmission system |
| CN115808633A (en) * | 2022-12-19 | 2023-03-17 | 浙江大学 | POA-SVR-based method for monitoring state of energy storage battery in island environment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11323176B2 (en) * | 2020-10-01 | 2022-05-03 | Viavi Solutions Inc | Modular cell site installation, testing, measurement, and maintenance tool |
-
2023
- 2023-05-12 CN CN202310538135.2A patent/CN116633433B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107917734A (en) * | 2017-11-29 | 2018-04-17 | 国网吉林省电力有限公司信息通信公司 | Cable's Fault Forecasting Methodology based on temperature and resistance |
| CN109474333A (en) * | 2018-12-27 | 2019-03-15 | 国网山西省电力公司晋中供电公司 | A kind of electric power optical cable real-time monitoring protection system based on deep learning |
| CN115098687A (en) * | 2022-07-18 | 2022-09-23 | 国家电网有限公司信息通信分公司 | Alarm checking method and device for scheduling operation of electric power SDH optical transmission system |
| CN115808633A (en) * | 2022-12-19 | 2023-03-17 | 浙江大学 | POA-SVR-based method for monitoring state of energy storage battery in island environment |
Non-Patent Citations (3)
| Title |
|---|
| 基于T-S模糊FTA的远程故障诊断方法研究;李文锋;游庆和;廖强;须民健;;控制工程(第09期);第1703-1708页 * |
| 李文锋 ; 游庆和 ; 廖强 ; 须民健 ; .基于T-S模糊FTA的远程故障诊断方法研究.控制工程.2018,(第09期),第1703-1708页. * |
| 浅谈国际上光伏发电故障诊断的统计分析方法;黄东风;姚烨彬;朱正菲;;能源与环境(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116633433A (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116633433B (en) | Model-driven OPGW optical cable fault diagnosis and positioning method | |
| Wu et al. | One-dimensional CNN-based intelligent recognition of vibrations in pipeline monitoring with DAS | |
| CN108932480B (en) | Distributed optical fiber sensing signal feature learning and classifying method based on 1D-CNN | |
| CN102027338B (en) | Signal judgment method, signal judgment apparatus, and signal judgment system | |
| CN114692681B (en) | SCNN-based distributed optical fiber vibration and acoustic wave sensing signal identification method | |
| CN109344195A (en) | Pipe safety event recognition and Knowledge Discovery Method based on HMM model | |
| CN112598151A (en) | High-voltage cable surface temperature prediction method in cable trench laying mode | |
| CN114528773B (en) | Track traffic stray current waveform prediction system and method based on big data analysis | |
| CN114684217A (en) | Rail transit health monitoring system and method | |
| CN109189622A (en) | Interface test method and device, electronic equipment, storage medium | |
| CN115017828A (en) | Power cable fault identification method and system based on bidirectional long-short-time memory network | |
| CN117353811B (en) | Multi-working-condition monitoring and analyzing method for electric power optical communication system | |
| CN112767351B (en) | Substation equipment defect detection method based on sensitive position dependence analysis | |
| CN117872219A (en) | Open-circuit fault diagnosis method and system for train traction converter | |
| Jaw et al. | Wind adaptive modeling of transmission lines using minimum description length | |
| CN116682045A (en) | Beam pumping unit fault detection method based on intelligent video analysis | |
| CN116660678A (en) | Evaluation system for power transmission network fault distance measurement and fault | |
| Coulibaly et al. | Explainability with association rule learning for weather forecast | |
| CN113344915B (en) | Method and system for detecting defects of key parts of power transmission line | |
| CN115907228A (en) | Short-term power load prediction analysis method based on PSO-LSSVM | |
| CN114722721A (en) | Power transformer health state evaluation method based on deep coding and decoding convolutional network | |
| CN114580307A (en) | Distributed power supply system electricity-related safety sensing method considering rainstorm space-time distribution | |
| CN114611788A (en) | Cold weather objective judging method based on GRU network | |
| CN118425687B (en) | Power transmission cable fault monitoring method and system based on traveling wave characteristics | |
| Zhao et al. | Prediction Method of Optical Cable Line Fault Probability Based on Improved KNN 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240207 Address after: 130000 no.10388, Renmin Street, Nanguan District, Changchun City, Jilin Province Applicant after: STATE GRID JILIN ELECTRIC POWER SUPPLY Co. Country or region after: China Applicant after: INFORMATION COMMUNICATION COMPANY OF STATE GRID JILIN ELECTRIC POWER Co.,Ltd. Applicant after: Changchun University of technology high tech Industry Co.,Ltd. Address before: 130000 no.10388, Renmin Street, Nanguan District, Changchun City, Jilin Province Applicant before: STATE GRID JILIN ELECTRIC POWER SUPPLY Co. Country or region before: China Applicant before: INFORMATION COMMUNICATION COMPANY OF STATE GRID JILIN ELECTRIC POWER Co.,Ltd. Applicant before: CHANGCHUN University OF SCIENCE AND TECHNOLOGY |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |