CN113221068A - SSTDR-based photovoltaic array fault detection method - Google Patents

SSTDR-based photovoltaic array fault detection method Download PDF

Info

Publication number
CN113221068A
CN113221068A CN202110503652.7A CN202110503652A CN113221068A CN 113221068 A CN113221068 A CN 113221068A CN 202110503652 A CN202110503652 A CN 202110503652A CN 113221068 A CN113221068 A CN 113221068A
Authority
CN
China
Prior art keywords
photovoltaic array
detection
calculating
value
sstdr
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.)
Granted
Application number
CN202110503652.7A
Other languages
Chinese (zh)
Other versions
CN113221068B (en
Inventor
李智华
吴春华
杨展飞
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.)
Shanghai Yanxin Electronic Technology Co ltd
Huangshan Dongan Xin'gao Energy Technology Co ltd
Original Assignee
Shanghai Yanxin Electronic Technology Co ltd
Huangshan Dongan Xin'gao Energy 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 Shanghai Yanxin Electronic Technology Co ltd, Huangshan Dongan Xin'gao Energy Technology Co ltd filed Critical Shanghai Yanxin Electronic Technology Co ltd
Priority to CN202110503652.7A priority Critical patent/CN113221068B/en
Publication of CN113221068A publication Critical patent/CN113221068A/en
Application granted granted Critical
Publication of CN113221068B publication Critical patent/CN113221068B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
    • H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Analysis (AREA)
  • Biophysics (AREA)
  • Computational Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Economics (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Databases & Information Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • Photovoltaic Devices (AREA)

Abstract

The invention discloses a photovoltaic array fault detection method based on SSTDR, which comprises the following steps: the method comprises the following steps: collecting and calculating a cross-correlation value, and forming a detection oscillogram with the distance between the cross-correlation value and the cable; step two: subtracting the detection waveform under the fault condition from the detection waveform under the normal condition; step three: calculating to obtain data characteristics; step four: inputting the data characteristics into a trained BP neural network; step five: calculating the fitness value of each classification result; step six: and taking the category of the maximum fitness value as a fault type. Compared with the conventional electrical detection method, the method has the advantages that the high-frequency detection signals are sent to the photovoltaic array branch, and the cross correlation between the incident signals and the reflected signals is analyzed to realize fault detection; the photovoltaic array output voltage, current, temperature, irradiance and other parameters are measured without additionally adding a sensor, and online detection can be carried out; and the photovoltaic array fault diagnosis is realized by combining a BP neural network.

Description

SSTDR-based photovoltaic array fault detection method
Technical Field
The invention belongs to the field of photovoltaic array fault detection, and particularly relates to a photovoltaic array fault detection method based on SSTDR.
Background
Photovoltaic system often installs in the place that illumination is sufficient, natural condition is abominable relatively, and subassembly and cable run can be because phenomena such as ageing, animal are grabbed and are bitten make the circuit damaged, the connector corrodes to lead to photovoltaic system generating efficiency, electric, reliability and security to reduce, the incident can take place finally. Past accident analysis showed that: a large part of the faults of the photovoltaic system are faults occurring on the direct current side of the photovoltaic system. Therefore, with the popularization and application of the distributed photovoltaic system, it is necessary to realize the online fault diagnosis of the dc side of the photovoltaic system.
For short-circuit faults of a photovoltaic array, a conventional detection and protection method is still to connect an overcurrent protection device (OCPDs) in series with a photovoltaic string, however, due to the nonlinear output characteristic, the current limiting characteristic, even the Maximum Power Point Tracker (MPPT) and other reasons of the photovoltaic array, some faults in the photovoltaic array, such as short-circuit faults, open-circuit faults, local shadows and the like, may not be distinguished and cleared by the OCPDs. Particularly, for distinguishing the local shadow and the short-circuit fault, the change situation of the voltage and the current directly is difficult to distinguish, which brings great challenges to the judgment of the fault.
Although the probability of a short-circuit fault occurring is much less than compared to a ground fault, once it occurs, it may cause a current to flow in a reverse direction in the fault string, with serious consequences.
For open-circuit faults of a photovoltaic array, the most common detection method is to collect output current and voltage signals of a photovoltaic system and the like for analysis and fault diagnosis, but misjudgment is easily caused due to the fact that the photovoltaic module is easy to age due to long service time, the line is easy to age, and the like.
Disclosure of Invention
The invention aims to overcome the problems in the prior art and provides a photovoltaic array fault detection method based on SSTDR, namely a photovoltaic array fault detection and diagnosis method based on a spread spectrum time domain reflection method. Compared with the conventional electrical detection method, the method has the advantages that the fault detection is realized by sending high-frequency detection signals to the photovoltaic array branch and analyzing the cross correlation between incident signals and reflected signals; the photovoltaic array output voltage, current, temperature, irradiance and other parameters are measured without additionally adding a sensor, and online detection can be carried out; and the photovoltaic array fault diagnosis is realized by combining a BP neural network.
In order to achieve the technical purpose and achieve the technical effect, the invention is realized by the following technical scheme:
a SSTDR-based photovoltaic array fault detection method, the method comprising the steps of:
the method comprises the following steps: collecting and calculating a cross-correlation value, and forming a detection oscillogram with the distance between the cross-correlation value and the cable;
step two: subtracting the detection waveform under the fault condition from the detection waveform under the normal condition;
step three: calculating to obtain data characteristics;
step four: inputting the data characteristics into a trained BP neural network;
step five: calculating the fitness value of each classification result;
step six: and taking the category of the maximum fitness value as a fault type.
Further, the collecting and calculating the cross-correlation value in the first step comprises the following steps:
s101: the PN sequence forms a high-frequency detection signal after being modulated by sine waves;
s102: after analog-to-digital conversion, the high-frequency detection signal is injected into the cable to be detected as an incident signal;
s103: the incident signal is transmitted in the cable and meets an impedance mismatching point to form a reflected signal;
s104: and performing analog-to-digital conversion on the reflected signal, performing correlation operation on the reflected signal and the high-frequency detection signal, and outputting the result.
Further, the output result of the correlation operation in S104 is as follows:
Figure BDA0003057436740000031
further, the BP neural network in the fourth step specifically includes the following steps:
s201: initialization: randomly giving the weight and the offset of each connection layer to be a non-zero value, and determining an excitation function;
s202: determining input and output of each layer;
s203: forward propagation: calculating the output of the network and the neuron error;
s204: and (3) back propagation: and updating the weight and the threshold of each layer according to the neuron error, stopping if the error or the cycle number meets the requirement, and otherwise, turning to the step S203.
Further, the three data characteristics of the step include a peak value, an absolute average value, a square root amplitude value and an average value.
The invention has the beneficial effects that:
1. compared with the conventional electrical detection method, the photovoltaic array fault detection and diagnosis method based on the spread spectrum time domain reflection method has the advantages that the fault detection is realized by sending high-frequency detection signals to the photovoltaic array branches and analyzing the cross correlation between incident signals and reflected signals; the photovoltaic array output voltage, current, temperature, irradiance and other parameters are measured without additionally adding a sensor, and online detection can be carried out; and the photovoltaic array fault diagnosis is realized by combining a BP neural network.
2. Under different fault conditions of the photovoltaic array, the SSTDDR-based test waveform and amplitude have obvious difference, can be used as an input criterion of a fault diagnosis algorithm, and has strong anti-interference performance and can be researched through simulation.
3. On the basis of fault detection of the photovoltaic array based on SSTDR, fault diagnosis of the photovoltaic array can be realized by combining a BP neural network.
4. Theoretical and technical references can be provided for SSTDDR-based photovoltaic array health status detection.
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 application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a photovoltaic array fault detection and diagnosis flow diagram of the present invention;
FIG. 2 is a block diagram of SSTDDR detection in the present invention;
FIG. 3 is the basic structure of BP neural network in the present invention;
FIG. 4 is a result of diagnosing a photovoltaic array fault by the BP neural network in 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.
A SSTDR-based photovoltaic array fault detection method as shown in fig. 1, the method comprising the steps of:
the method comprises the following steps: collecting and calculating a cross-correlation value, and forming a detection oscillogram with the distance between the cross-correlation value and the cable;
step two: subtracting the detection waveform under the fault condition from the detection waveform under the normal condition;
step three: calculating to obtain data characteristics of peak value, absolute average value, square root amplitude and average value;
step four: inputting the data characteristics into a trained BP neural network;
step five: calculating the fitness value of each classification result;
step six: and taking the category of the maximum fitness value as a fault type.
As shown in fig. 2, based on a Spread Spectrum Time Domain Reflection (SSTDR) method, the collecting and calculating of the cross-correlation value in the first step includes the following steps:
s101: the PN sequence forms a high-frequency detection signal after being modulated by sine waves;
s102: after analog-to-digital conversion, the high-frequency detection signal is injected into the cable to be detected as an incident signal;
s103: the incident signal is transmitted in the cable and meets an impedance mismatching point to form a reflected signal;
s104: and performing analog-to-digital conversion on the reflected signal, performing correlation operation on the reflected signal and the high-frequency detection signal, and outputting the result.
The output result of the correlation operation in S104 is as follows:
Figure BDA0003057436740000051
where s (t) is the incident signal; reflected signal r (t) ═ Σ aks(t-td)+n(t),akN (t) is a noise signal, tdIs the delay time of the reflected signal. If the background noise is white gaussian noise, s (t) is independent of n (t), i.e. the calculation result r (t) is only related to the cross-correlation value of the incident signal and the reflected signal.
The BP neural network algorithm belongs to a supervised learning algorithm and is also the most successful neural network learning algorithm at present. The main idea is as follows: for a given training set, the mapping relation between the input and the output of the given training set does not need to be determined, only the input sample needs to be calculated according to a preset selected learning algorithm to enable the error between the obtained result and the output sample to be as small as possible, then the error is propagated reversely, and when the finally obtained result and the output of the sample meet the error value or reach the preset training times, the training is finished. The BP neural network is mainly applied to the four aspects of function approximation, mode identification, classification problem and data compression.
The BP neural network in the fourth step specifically comprises the following steps:
s201: initialization: randomly giving the weight and the offset a of each connection layerj、bjA non-zero value and determines the excitation function as a Sigmoid function:
g(x)＝1/(1+e-x)；
s202: determining input and output of each layer:
if is Xk＝[xk1,xk2,…,xkM](k-1, 2, …, N) is an input vector, N is the number of training samples, Hk(n)＝[hk1(n),hk2(n),…,hkM(n)]Is the output of the hidden layer, wherein
Figure BDA0003057436740000061
Is the output of the output layer, wherein
Figure BDA0003057436740000062
To expect an output, FIG. 3 shows a typical 3-layer forward network with 4 inputs and 4 outputs;
s203: forward propagation: calculating the output of the network and the neuron error;
s204: and (3) back propagation: and updating the weight and the threshold of each layer according to the neuron error, stopping if the error or the cycle number meets the requirement, and otherwise, turning to the step S203.
The problem of fault detection of the photovoltaic array can be regarded as a four-value classification problem, and in order to obtain a better distinguishing effect, a peak value, an absolute average value, a square root amplitude value and an average value are selected as input samples through comprehensive comparison:
1. peak value:
Xpeak＝max{x1,x2,x3…xN}
2. absolute average value:
Figure BDA0003057436740000071
3. square root amplitude:
Figure BDA0003057436740000072
4. average value:
Figure BDA0003057436740000073
the output parameters are also 4, respectively healthy state, ground fault, short circuit fault and open circuit fault. The input parameter normalization formula is:
Figure BDA0003057436740000074
considering that the obtained data of the experimental waveform photovoltaic panel end mainly occurs about x meters away from the head end (namely the distance between the incident end and the combiner box), according to the experimental waveform, the waveforms of the rest places can cause errors on the experimental result if the calculation is considered, and the experimental incident end is about 26 meters away from the photovoltaic panel, so the first 5-150 data (which is the waveforms near the combiner box) are taken for processing (note: the first 5 data are not mainly taken because they are close to the incident end, the incident end itself is the impedance mismatching point, and the interference needs to be eliminated), taking the failure parameters of the photovoltaic module string as an example, the results obtained after normalization are shown in the following table:
Figure BDA0003057436740000081
in conclusion, dozens of groups of data of each type are respectively sampled to perform data analysis under four states of the photovoltaic array health state, the grounding fault state, the short-circuit fault state and the open-circuit fault state, the photovoltaic module string and the photovoltaic array fault diagnosis accuracy rate are separately calculated and averaged, and after the obtained results are integrated, as shown in fig. 4, the average accuracy rate of the fault diagnosis of the photovoltaic array through the BP neural network reaches more than 85%, the judgment accuracy rate of the health state and the grounding fault state can almost reach 100%, and the experimental result shows that the method has a good detection effect.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed.

Claims (5)

1. A photovoltaic array fault detection method based on SSTDR is characterized in that: the method comprises the following steps:
the method comprises the following steps: collecting and calculating a cross-correlation value, and forming a detection oscillogram with the distance between the cross-correlation value and the cable;
step two: subtracting the detection waveform under the fault condition from the detection waveform under the normal condition;
step three: calculating to obtain data characteristics;
step four: inputting the data characteristics into a trained BP neural network;
step five: calculating the fitness value of each classification result;
step six: and taking the category of the maximum fitness value as a fault type.
2. The SSTDR-based photovoltaic array fault detection method of claim 1, wherein: the collecting and calculating of the cross-correlation value in the first step comprises the following steps:
s101: the PN sequence forms a high-frequency detection signal after being modulated by sine waves;
s102: after analog-to-digital conversion, the high-frequency detection signal is injected into the cable to be detected as an incident signal;
s103: the incident signal is transmitted in the cable and meets an impedance mismatching point to form a reflected signal;
s104: and performing analog-to-digital conversion on the reflected signal, performing correlation operation on the reflected signal and the high-frequency detection signal, and outputting the result.
3. The SSTDR-based photovoltaic array fault detection method of claim 2, wherein: the output result of the correlation operation in S104 is as shown in the following formula:
Figure FDA0003057436730000011
4. the SSTDR-based photovoltaic array fault detection method of claim 1, wherein: the BP neural network in the fourth step specifically includes the following steps:
s201: initialization: randomly giving the weight and the offset of each connection layer to be a non-zero value, and determining an excitation function;
s202: determining input and output of each layer;
s203: forward propagation: calculating the output of the network and the neuron error;
s204: and (3) back propagation: and updating the weight and the threshold of each layer according to the neuron error, stopping if the error or the cycle number meets the requirement, and otherwise, turning to the step S203.
5. The SSTDR-based photovoltaic array fault detection method of claim 1, wherein: the three data characteristics of the step comprise a peak value, an absolute average value, a square root amplitude value and an average value.
CN202110503652.7A 2021-05-10 2021-05-10 Photovoltaic array fault detection method based on SSTDR Active CN113221068B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110503652.7A CN113221068B (en) 2021-05-10 2021-05-10 Photovoltaic array fault detection method based on SSTDR

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110503652.7A CN113221068B (en) 2021-05-10 2021-05-10 Photovoltaic array fault detection method based on SSTDR

Publications (2)

Publication Number Publication Date
CN113221068A true CN113221068A (en) 2021-08-06
CN113221068B CN113221068B (en) 2023-12-01

Family

ID=77093911

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110503652.7A Active CN113221068B (en) 2021-05-10 2021-05-10 Photovoltaic array fault detection method based on SSTDR

Country Status (1)

Country Link
CN (1) CN113221068B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113376494A (en) * 2021-08-16 2021-09-10 国网江苏省电力有限公司电力科学研究院 Method for detecting potential defects of fire hidden danger of cable
CN113746132A (en) * 2021-08-11 2021-12-03 国网江苏省电力有限公司 Photovoltaic power station based on cloud edge cooperation and control method thereof
CN117031235A (en) * 2023-07-31 2023-11-10 中南大学 IGBT fault diagnosis method and device based on time domain reflection signals

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108829949A (en) * 2018-05-25 2018-11-16 南京航空航天大学 Aircraft secondary distribution system PHM system architecture
CN108872751A (en) * 2018-07-05 2018-11-23 西南交通大学 A kind of method for diagnosing faults of three level Cascade H-Bridge Inverter neural network based
CN109975673A (en) * 2019-04-23 2019-07-05 辽宁工程技术大学 A kind of photovoltaic micro DC side fault electric arc recognition methods
US20190242936A1 (en) * 2018-02-05 2019-08-08 Wuhan University Fault diagnosis method for series hybrid electric vehicle ac/dc converter
CN110488161A (en) * 2019-07-23 2019-11-22 南京航空航天大学 A kind of detection of multi-load series arc faults and localization method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190242936A1 (en) * 2018-02-05 2019-08-08 Wuhan University Fault diagnosis method for series hybrid electric vehicle ac/dc converter
CN108829949A (en) * 2018-05-25 2018-11-16 南京航空航天大学 Aircraft secondary distribution system PHM system architecture
CN108872751A (en) * 2018-07-05 2018-11-23 西南交通大学 A kind of method for diagnosing faults of three level Cascade H-Bridge Inverter neural network based
CN109975673A (en) * 2019-04-23 2019-07-05 辽宁工程技术大学 A kind of photovoltaic micro DC side fault electric arc recognition methods
CN110488161A (en) * 2019-07-23 2019-11-22 南京航空航天大学 A kind of detection of multi-load series arc faults and localization method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MASHAD UDDIN SALEH: "An Overview of Spread Spectrum Time Domain Reflectometry Responses to Photovoltaic Faults", IEEE *
孟佳彬: "基于SSTDR的光伏系统对地故障检测方法", 太阳能学报, vol. 41, no. 10 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113746132A (en) * 2021-08-11 2021-12-03 国网江苏省电力有限公司 Photovoltaic power station based on cloud edge cooperation and control method thereof
CN113746132B (en) * 2021-08-11 2024-01-30 国网江苏省电力有限公司 Photovoltaic power station based on cloud edge cooperation and control method thereof
CN113376494A (en) * 2021-08-16 2021-09-10 国网江苏省电力有限公司电力科学研究院 Method for detecting potential defects of fire hidden danger of cable
CN117031235A (en) * 2023-07-31 2023-11-10 中南大学 IGBT fault diagnosis method and device based on time domain reflection signals
CN117031235B (en) * 2023-07-31 2024-07-16 中南大学 IGBT fault diagnosis method and device based on time domain reflection signals

Also Published As

Publication number Publication date
CN113221068B (en) 2023-12-01

Similar Documents

Publication Publication Date Title
CN113221068A (en) SSTDR-based photovoltaic array fault detection method
Saini et al. Detection and classification of power quality disturbances in wind‐grid integrated system using fast time‐time transform and small residual‐extreme learning machine
Roy et al. PSD based high impedance fault detection and classification in distribution system
Luo et al. Stacked auto-encoder based fault location in VSC-HVDC
CN111562517B (en) NPC three-level inverter switching tube open-circuit fault diagnosis method
CN104730423A (en) Island effect detecting method of grid-connected photovoltaic power system
CN113985194A (en) Power distribution network fault positioning method based on stack self-encoder
CN103901318B (en) The method of positioning both ground failure and insulation degraded condition in energy conversion system
Davarifar et al. Partial shading fault diagnosis in PV system with discrete wavelet transform (DWT)
Pan et al. Learning approach based DC arc fault location classification in DC microgrids
CN112946425A (en) Fault positioning method for mining travelling wave time-frequency domain characteristics by utilizing deep learning
Chang et al. Anomaly detection for shielded cable including cable joint using a deep learning approach
CN113610119B (en) Method for identifying power transmission line development faults based on convolutional neural network
Lout et al. Current transients based phase selection and fault location in active distribution networks with spurs using artificial intelligence
Kale et al. Detection and classification of faults on parallel transmission lines using wavelet transform and neural network
CN113514743A (en) Construction method of GIS partial discharge pattern recognition system based on multi-dimensional features
Mahela et al. A protection scheme for distribution utility grid with wind energy penetration
Aslan et al. ANN based fault location for medium voltage distribution lines with remote-end source
CN115498956A (en) Photovoltaic array series arc fault diagnosis method
Fahim et al. An agreement based dynamic routing method for fault diagnosis in power network with enhanced noise immunity
TWI379093B (en) Method and portable device for fault diagnosis of photovoltaic power generating system
Cheong et al. Accurate fault location in high voltage transmission systems comprising an improved thyristor controlled series capacitor model using wavelet transforms and neural network
CN113203916A (en) Inside and outside fault identification method and system of extra-high voltage direct current transmission line based on sym8 wavelet packet transformation
Kingston et al. Spread Spectrum Time Domain Reflectometry (SSTDR) digital twin simulation of photovoltaic systems for fault detection and location
Park et al. AI-enhanced time–frequency domain reflectometry for robust series arc fault detection in DC grids

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
GR01 Patent grant
GR01 Patent grant