Conference PaperPDF Available

An intelligent method for fault diagnosis in photovoltaic systems

An Intelligent Method for Fault Diagnosis in
Photovoltaic Systems
Department of electrical engineering
Mohammed V University in Rabat
Ecole Mohammadia d'Ingenieurs
Rabat, Morocco
Mohammed Ouassaid
Department of electrical engineering
Mohammed V University in Rabat
Ecole Mohammadia d'Ingenieurs
Rabat, Morocco
AbstractThis paper presents a diagnostic method based on
IV characteristic analysis and Artificial Neural Networks
(ANN). A number of attributes are estimated using a simulation
model based on a set of working conditions such as solar
irradiance and module's temperature. The estimated attributes
are then compared with those obtained from the real PV array
measurements, which lead to the detection of possible faulty
operating conditions. After detecting the presence of possible
fault, tow algorithms are developed in order to isolate and
identify eight different types of faults. The simulation results
show that the proposed method can detect and classify the
different faults occurring in a PV array with a high accuracy.
KeywordsPhotovoltaic, Fault detection, Fault diagnosis,
Fault localization, ANN.
The use of photovoltaic (PV) systems is now increasing
rapidly all over the world. With this increase in PV systems,
the number of problems and failures is also increasing. The
importance of service and maintenance is therefore growing.
The need for optimal functioning of PV systems is linked to
the recent interest in fault diagnosis techniques, which are
today more and more developed in the literature.
Nowadays, many diagnostic techniques are developed for
possible fault detection in PV systems. Generally, fault
detection techniques for PV systems can be grouped as visual
(browning, discoloration, surface soiling, and delamination),
thermal (hot spot), and electrical (transmittance line diagnosis,
dark/illuminated current-voltage measurement, and Radio
frequency measurement) [1]. In this paper, we used an
electrical method to detect the investigated faults. Electrical
methods for fault detection in photovoltaic systems can be
grouped as:
- Methods that do not require climate data (solar irradiance
and modules temperature): in [2], the Earth Capacitance
Measurement (ECM) method was used as an electrical
technique for detecting where a photovoltaic module in a
string has been disconnected. In [3], The Time-Domain
Reflectometry (TDR) technique was used to detect the
disconnection of a PV string as well as the impedance
change due to degradation.
- Methods based on the evaluation of the currentvoltage
characteristic (IV characteristic): in [4], the (dI/dV)-V
characteristic was used to detect the partial shadow fault
in a PV array. In [5], a method based on the evaluation of
some current and voltage indicators was introduced as an
automatic fault detection for Grid-Connected Photovoltaic
(GCPV) systems;
- Methods based on the Maximum Power Point Tracking
(MPPT) approach: an automatic supervision and fault
detection procedure based on the analysis of the power
losses was proposed in [6]. This method leads to the
identification of three groups of faults (faulty string,
faulty module, and a group of different faults including
partial shadow, ageing, and MPPT failure). The technique
developed in [7] is based on the comparison between the
simulated and the measured string powers. This method is
even able to determine the number of open and short-
circuited PV modules in a string;
- Methods that use the Artificial Intelligence (AI): in [8] a
learning technique based on Expert Systems was
developed to identify two types of fault (shading effect
and inverter's failure). In [9], a method for the
identification of short-circuited PV modules is presented.
An ANN is used in order to classify different types of
faults occurring in a PV array in [10]. The ANN takes as
inputs the voltage and the current at maximum power
point, as well as the temperature of the PV modules. The
method presented in [11] uses tow algorithms. The first
algorithm is based on a signal threshold approach that
isolates faults having different combinations of attributes.
The second is an ANN used to distinguish between faults
having the same signature. This technique is able to detect
eight different types of faults. Different methods based on
the Takagie Sugeno Kahn Fuzzy Rule (TSKFRBS) have
been described in [12, 13].
In this paper, an automatic fault diagnosis method is
presented. It allows the detection and the localization of faults
occurring in: PV cells, PV modules, PV strings, and bypass-
diodes. The proposed technique is based on the analysis of a
set of attributes of the IV characteristic. To expand the
number of detected faults the analysis is performed using two
different Algorithms:
978-1-5386-1516-4/17/$31.00 ©2017 IEEE
3rd International Conference on Electrical and Information Technologies ICEIT’2017
Yassine Chouay *
- Algorithm 1 uses the signal threshold approach based on
the IV characteristic analysis, which identifies faults
affecting the IV characteristic differently.
- Algorithm 2 consists of an ANN-based approach to
identify the faults that are characterized by the same
effect on the IV characteristic.
Generally, faults occurring in a PV system are mainly
related to the PV array, the storage system, the inverter, and
the grid. The work presented in this paper intends to detect the
faults occurring in the PV array (DC side). According to Table
I, eight different faults are detected. These types of faults are
usually connected to: the failure of a solar cell or a PV
module, the degradation effect, a line disconnection, corrosion
and manufacturing defects, the presence of shadow, the effect
of soiling, and etc.
As shown in Fig. 1, the difference between the simulated
and the measured PV system output power (ΔP) is compared
with a threshold (Th) to decide whether the system is
functioning in faulty mode. Then, in order to identify and
determine the fault type, the main attributes in the IV
characteristic of each string forming the PV array are analyzed.
The schematic of the developed fault diagnosis system is
depicted in Fig. 2.
A. Attributes identication
Before developing the fault detection algorithm, it’s
necessary to understand the effect of each fault on the normal
functioning. Therefore, a number of simulations have been
carried out considering both normal operation and different
fault conditions. The changes that affect the IV characteristic
of a PV string are presented in Fig. 3. The analysis of these
simulations led to the identification of five situations of
- A reduction in the short circuit current (FIsc);
- A reduction in the open circuit voltage (FVoc);
- An increase or a reduction in the output current (FIm);
- An increase or a reduction in the output voltage (FVm);
- An increase in the number of MPPs in the IV
characteristic (N). In case of partial shading the difference
between the simulated and the measured number of MPPs
(ΔN) is not null.
B. Algorithm 1 (Signal threshold based approach)
The first algorithm isolates the faults that have a different
combination of attributes. Firstly, the relative differences
between the simulated and measured PV string attributes are
compared with some predefined thresholds. The simulated I
V characteristics are obtained from a Simulink model based
on the values of solar irradiance and module temperature.
The thresholds are calculated according to the maximum
Short circuit fault in any bypass diode, cell or
Inversed bypass diode, cell or module.
Shunted bypass diode, cell or module.
Open circuit fault in any cell or module.
Connection resistance between PV modules.
Shading effect in the modules with normal
operation of other components of PV string.
Shadow effect in a group of cells equipped by an
open-circuited bypass diode.
Shadow effect in a group of modules equipped by
a connection fault.
Fig. 1. Flow chart of the proposed fault detection technique.
Fig. 2. Schematic of the fault diagnosis technique.
Data from the
DAQ (G, T)
PV module parameters,
number of strings and
Electrical data from
, Vmaes)
Simulated PV model
(Isim, Vsim)
Start faults
isolation algorithms
PV array
Attributes calculation
Real PV
ANN Algorithm
3rd International Conference on Electrical and Information Technologies ICEIT’2017
error introduced by the measurement noise and the model
- The sensors used to test the proposed diagnostic system
are supposed within the specifications required by the IEC
61724 standard [14] indicating a relative error of 1%, 1%,
and 2% for current, voltage, and power measurement,
- The model uncertainty is related to sensor noise and the
manufacturing tolerance. According to [15], the
maximum error introduced by this uncertainty is
calculated by adding a dispersion parameter to the
simulation model parameters. The obtained relative errors
associated with current, voltage, and power are equal to
3.0%, 2.9%, and 5.9%, respectively.
Thresholds (Th, TCand TV) for the first algorithm are
obtained by adding errors introduced by both model and
measurement uncertainties:
(2% 5.9%)
(1% 3%)
(1% 2.9% )
Th P
Fig. 4 illustrates the flowchart of Algorithm 1 that allows
the isolation of six different situations: F4, F5, F6, F7, F8, and
a group of faults gathering F1, F2, F3, and F5.
C. Algorithm 2 (ANN based approach)
As shown in Fig. 4, the first algorithm cannot differentiate
between a group of faults including F1, F2, F3 and F5 because
they have the same fault signature. Furthermore, there are
some differences in the symptoms of the IV characteristic
under these faults at the same conditions. Therefore, in order
to isolate these faults, an ANN model has been developed as
1) Selection of the input and output variables
The ANN architecture consists of three neurons in the input
layer corresponding to the ratio between the measured and the
simulated values of the open circuit voltage (RVoc), the
maximum power point current (RIm), and the maximum power
point voltage (RVm). One neuron in the output layer
corresponding to the fault class.
2) Selection of the network structure
The network used in this work is a Multilayer Perceptron
(MLP). The MLP structure consists of one hidden layer
containing 40 nodes as represented in Fig. 5. The transfer
function used in this architecture is the logarithmic sigmoidal
3) Network training and test
The network is trained with the Levenberg-Marquardt (LM)
algorithm. The training data was generated from a set of
simulations of both normal and faulty operations for the four
Fig. 3.
IV characteristics of a PV string in normal and faulty operations
: (a).
without shading
effect. (b). with shading effect.
Fig. 4. Block diagram of Algorithm 1.
Calculation of the attributes
strings amplitude
|∆N|> 0
circuit F4
effect with
faulty bypass
diode F7
Group of faults:
circuited diodes
Inversed diodes F2
Shunted diodes F3
-Connection fault F5
fault F5
Shadow effect
with connection
fault F8
Partia l shadow
without any fault on
bypass diode F6
ANN Algorithm
3rd International Conference on Electrical and Information Technologies ICEIT’2017
faults. 80% of the patterns have been used for the training,
while 20% have been used for testing and validating the
In order to test the effectiveness of this intelligent method a
simulation of both normal and faulty operation was carried out
in Matlab/Simulink environment. The detection program takes
attributes from two simulated PV systems, the first represents
the real PV array (contain different faults) and the other
represents the normal functioning.
A. Performance of the proposed technique
1) Performance of Algorithm 1
In order to verify the performance of the first Algorithm, a
PV array formed by one string of five MSX60 series-
connected PV modules having the electrical characteristics
illustrated in Table II has been considered, and different cases
of study have been examined in STC:
- Case 1: The connection resistance between two modules
was increased by 20 Ω;
- Case 2: one module was 50% shaded and all bypass
diodes open-circuited in this module;
- Case 3: two modules were shaded (the shading proportion
was 50% for the first module and 25% for the second);
The calculated thresholds, attributes and the Algorithm 1
decision are reported in Table III.
The simulation results show that the first algorithm is able
to localize and identify correctly the faults in the examined PV
2) Performance of Algorithm 2
The network was trained using a set of data generated from
the simulation results of the four investigated faults, and with
reference to Fig. 6. (a) the minimum Mean Square Errors
(MSE) achieved while training, testing and validating the
model are 0.013, 0.032 and 0.0057, respectively. In order to
examine the effectiveness of the proposed ANN-based
approach, Fig. 6. (b) represents the classification confusion
Fig. 5. Schematic of the used ANN architecture.
40 Neurons
F1, F2, F3, or F4
Fig. 6. (a). Evolution of the MSE for the MLP network. (b). Classication confusion matrix for the MLP network
AND 1000 W/M2.
3.5 A
17.1 V
59.85 W
3.8 A
21.1 V
3rd International Conference on Electrical and Information Technologies ICEIT’2017
matrix for the four considered faults. The green cells represent
the percentage of fault correctly classified, while the red ones
represent the wrong classifications.
The classification confusion matrix shows that 94.1% of the
training and testing samples were correctly classified, while
5.9% were not correctly classified. The false classifications
between F1 and F2 happened when the number of inversed
cells or bypass diodes was very low. The false classifications
between F3 and F5 occurred when the connected and shunt
resistances, had either a very low or a very high value.
B. Comparison
In order to confirm the effectiveness of the proposed
method, this one is compared with the method presented in [6]
that uses the power losses to detect and distinguish between
faults. The comparison between the attributes and the results
given by the two methods is presented in Table IV, for the
four different case studies. As can be noticed, the power losses
analysis method cannot identify the exact fault type.
This paper has proposed a fault diagnosis method is
conceived to detect and isolate eight faults occurring in a PV
array. Two different algorithms allow the isolation and
identification of faults. The first algorithm detects faults
having a different combination of attributes, whereas the
second use an ANN to discriminate between faults even if
they have the same signature. The simulation results
confirmed the performance of this technique by testing the
effectiveness of each algorithm individually. The results have
shown also that the proposed method detects and identify the
investigated faults with a high accuracy compared to other
[1] B. Ando, S. Baglio, A. Pistorio, G.M. Tina, C. Ventura, Sentinella:
smart monitoring of photovoltaic systems at panel level,IEEE Trans.
Instrum. Meas. vol. 64, august 2015, 2199.
[2] T. Takashima, J. Yamaguchi, K. Otani, T. Oozeki, K. Kato, M. Ishida,
Experimental studies of fault location in PV module strings,Sol.
Energy Mater Sol. Cells 93, 2009, pp. 10791082 .
[3] L. Schirone, F.P. Califano, M. Pastena, Fault detection in a
photovoltaic plant by time domain reflectometry,” Prog Photovolt Res
Appl, vol. 2, 1994, pp. 3544.
[4] M. Miwa, S. Yamanaka, H. Kawamura, H. Ohno, H. Kawamura,
“Diagnosis of a power output lowering of PV array with a (-dI/dV)V
characteristic,” in: Proceeding of IEEE 4th World Conference on
Photovoltaic Energy Conversion, Waikoloa, HI, 2006, pp. 24422445.
[5] S. Silvestre, M.A. da Silva, A. Chouder, D. Guasch, E. Karatepe, New
procedure for fault detection in grid connected PV systems based on the
evaluation of current and voltage indicators,Energy Convers. Manag.
vol. 86, 2014, pp. 241249.
[6] S. Silvestre, A. Chouder, E. Karatepe, Automatic supervision and fault
detection of PV systems based on power losses analysis,Energy
Convers. Manag. vol. 51, 2010, pp. 19291937.
[7] N. Gokmen, E. Karatepe, B. Celik, S. Silvestre, Simple diagnostic
approach for determining of faulted PV modules in string based PV
arrays,Sol. Energy, vol. 86, 2012, pp. 33643377.
[8] Y. Yagi, H. Kishi, R. Hagihara, T. Tanaka, S. Kozuma, T. Ishida, M.
Waki, M. Tanaka, S. Kiyama, Diagnostic technology and an expert
system for photovoltaic systems using the learning method,Sol. Energy
Mat. Sol. Cells, vol. 75, 2003, pp. 655663.
[9] S. Syafaruddin, E. Karatepe, T. Hiyama, Controlling of artificial neural
network for fault diagnosis of photovoltaic array,in: Proceedings of the
16th International Conference on Intelligent System Application to
Power Systems (ISAP), Greece, 2011, pp. 16.
[10] Z. Li, Y. Wang, D. Zhou, C. Wu, An intelligent method for fault
diagnosis in photovoltaic array,ICSC Part II CCIS, vol. 327, 2012, pp.
[11] W. Chine a, A. Mellit, V. Lughi, A. Malek d, G. Sulligoi, A. Massi
Pavan, A novel fault diagnosis technique for photovoltaic systems
based on artificial neural networks,Renewable Energy, vol. 90, 2016,
[12] P. Ducange, M. Fazzolari, B. Lazzerini, F. Marcelloni, An intelligent
system for detecting faults in photovoltaic fields, in: Proceedings of the
11th International Conference on Intelligent Systems Design and
Applications IEEE, Cordoba, Spain, 2011, pp. 13411346.
[13] L. Bonsignore, M. Davarifar, A. Rabhib, G.M. Tinaa, A. Elhajjaji,
Neuro-Fuzzy fault detection method for photovoltaic systems, Energy
Procedia,” vol. 62, 2014, pp. 431441.
[14] W. Xiao, W.G. Dunford, A. Capel,A novel modelling method for
photovoltaic cells”, in: Proceedings of the IEEE 35th, Annual Power
Electronics Specialists Conference (PESC), Germany, 2004, pp. 1950
[15] L. Bun, “Détection et localisation de défauts pour un système PV,” PhD
thesis, University of Grenoble, 2011.
Power losses analysis method
The proposed technique
Two shaded modules in the string.
=1, R
Faulty module.
Algorithme 1:
N=1, FIm=0.01, TC=0.16
Partial shadow without any
fault on bypass diode.
Connection resistance between two
modules is increased.
=1.47, R
Group of faults.
Algorithme 1:
N=0, FIsc =1.6, TC=0.16
Connectic fault.
Two short-circuited modules in the
=1, R
Faulty module.
Algorithme 1:
N=0, FIsc =0, FIm =0.02, TC= 0.16
Group of faults.
Algorithme 2:
RVoc=0.66, RVm=0.66, RIm=0.99
Cells, diodes, or modules are
short circuited.
String with one inversed module.
=1, R
Faulty module.
Algorithme 1:
N=0, FIsc=0, FIm=0.2,
TC=0.16, FVoc=65.8, TV=7.68
Group of faults.
Algorithme 2:
RVoc=0.66, RVm=0.62, RIm=0.97
Cells, diodes, or modules are
RC: Current ratio, RV
: Voltage ratio.
3rd International Conference on Electrical and Information Technologies ICEIT’2017
... In other cases, more than one approach is combined in a single algorithm as a hybrid diagnosis technique [9,10]. As in [9], the Output signal analysis method was combined with Support Vector Machine (SVM) to identify line-line faults. ...
... As in [9], the Output signal analysis method was combined with Support Vector Machine (SVM) to identify line-line faults. Alternatively, in [10] a model-based difference measurement technique is combined with an ANN approach to detect and identify several faults occurring in the PV string. ...
Full-text available
This paper proposes an improved method for fault diagnosis on the DC side of PV plant. The proposed technique relies on three-stage classification algorithms to detect and distinguish between eight of the most common faults occurring in the PV generator. The first part of the detection algorithm uses the power loss analysis approach to identify the presence of potential fault from the comparison of the measured and expected generated power. The second part relies on a comparison between the extracted and reference PV characteristic to identify the fault type. The last part is based on Support Vector Machine (SVM) algorithm that interferes to classify faults with the same signature. The simulation results have proven that the proposed method is capable of identifying and distinguishing between eight of the most common DC side faults with a 100% accuracy.
... In the fault classification context, there are different approaches, such as visual methods [18], thermographic image analysis methods [13], and mathematical methods using theoretical and simulated models of PV plants [19]. More recently, some machine learning-based techniques have been proposed, improving the classification performance in different cases, mainly including the shadowing and degradation of PV modules [9,20,21]. Notwithstanding, most of the methods are focused on simulated data and the authors do not present an extensive analysis of methods for online fault classification. ...
... With that, the real-time classification of faults is unfeasible, since the generation of the VxI curve requires the disconnection of the plant to connect the proposed equipment and perform the detection and classification. Following a similar idea, a detection and classification system is presented in [20], obtaining an accuracy of 94.1%. However, the authors also presented tests only in a simulation environment. ...
Full-text available
Photovoltaic (PV) energy use has been increasing recently, mainly due to new policies all over the world to reduce the application of fossil fuels. PV system efficiency is highly dependent on environmental variables, besides being affected by several kinds of faults, which can lead to a severe energy loss throughout the operation of the system. In this sense, we present a Monitoring System (MS) to measure the electrical and environmental variables to produce instantaneous and historical data, allowing to estimate parameters that ar related to the plant efficiency. Additionally, using the same MS, we propose a recursive linear model to detect faults in the system, while using irradiance and temperature on the PV panel as input signals and power as output. The accuracy of the fault detection for a 5 kW power plant used in the test is 93.09%, considering 16 days and around 143 hours of faults in different conditions. Once a fault is detected by this model, a machine-learning-based method classifies each fault in the following cases: short-circuit, open-circuit, partial shadowing, and degradation. Using the same days and faults applied in the detection module, the accuracy of the classification stage is 95.44% for an Artificial Neural Network (ANN) model. By combining detection and classification, the overall accuracy is 92.64%. Such a result represents an original contribution of this work, since other related works do not present the integration of a fault detection and classification approach with an embedded PV plant monitoring system, allowing for the online identification and classification of different PV faults, besides real-time and historical monitoring of electrical and environmental parameters of the plant.
... Nowadays there are two paradigms for the faults detection in PVS. The first paradigm is found in the works reported by (Chaibi et al., 2019;Chouay & Ouassaid, 2018;Das et al., 2018;Dhimish et al., 2017;Fadhel et al., 2020;Hajji et al., 2020;Hu et al., 2017;Kumar et al., 2018;Lu et al., 2019;Mekki et al., 2016;Rouani et al., 2021;Sowthily et al., 2021;Yi & Etemadi, 2017). The procedures reported under this paradigm focus on the use of learning machines (supervised or unsupervised approach), which employ a coherent detection point of view. ...
Full-text available
Failures in photovoltaic systems are a problem of great importance because they cause a deterioration in the production of electrical energy, among which is the dust on the surface of the photovoltaic system. This paper proposes a method to detect dust on the surface of a photovoltaic system in series configuration. In addition, shows by visual inspection that the IV characteristic of a photovoltaic panel is equal to the IV characteristic of a photovoltaic system. To obtain the results, 120 signals were used, 60 for the design of the method and the rest for the validation of the method. The proposed method only yielded 2 false positives out of 30 signals where there was no fault present.
... The method presented herein is also based on a mathematical approach. Some of the latest techniques utilize the vast possibilities of machine learning (Kurukuru et al., 2019), and have the potential of enhancing the classification (Da Costa et al., 2019) performance in various areas, such as the degradation and shading effects affecting PV modules (Chouay and Ouassaid, 2018). ...
Full-text available
As decentralized energy supply systems are becoming more and more important for the global energy supply, – apart from a heightened focus on energy rationalization and energy efficiency – increasing the role of variable renewable energy sources, such as solar and wind energy, in energy consumption is gaining more and more significance. Since energy projects tend to be meant for the long term and involve considerable financial investments, it is indispensable to be aware of the country-specific regulatory background when establishing photovoltaic (PV) systems. The last few years have witnessed a trend that new PV power plants are mostly built using traditional crystalline PV technologies, which are prone to irreversible PV module damage due to shading effects. During the operation of PV power plants, anomalies causing loss of income and even fire hazard in extreme cases may occur. Thus, the identification of the problematic parts of the system is of utmost importance. This paper presents the energy relationships of shading by the example of a Hungarian PV system. The goal of this study is to introduce a methodology that can be used internationally to categorize the operational characteristics of the strings of PV power plants on the basis of monitoring data, which allows the assessment of the annual energy loss. The innovative novelty of the model is that its use can provide practical help for the operators of PV systems around the world, since the solution is easy to adapt to real-time supervisory and management platforms and it makes the localization of problematic strings possible, thusly allowing a more focused inspection of PV power plants. The novel practical benefit of the model is that by its use it becomes possible to detect any energy loss resulting from the spacing distance of the strings of PV power plants or faulty operation (the negative shading effects of trees and other objects, faulty inverter operation) by using a simpler calculating mechanism. The early detection of problems is essential for the protection of the PV modules, the subsequent reconstruction of the strings or even solving issues under guarantee. In addition, by assessing the annual energy loss caused by shading, it becomes possible to detect any negative change in the economic indicators of the investment.
... Several research works have been proposed to detect and diagnose PV system faults. For instance, authors in [8] suggest a diagnostic method based on I-V characteristic analysis and Artificial Neural Networks (ANN). This method allows the detection and localization of faults occurring in PV cells, PV modules, PV strings, and bypass diodes. ...
Full-text available
Grid-connected photovoltaic power systems always have a connection to a utility grid via a suitable inverter because a PV array only produces a DC power. This paper presents fault diagnosis and troubleshooting on 2.1 kW grid-connected photovoltaic power system in UiTM Pulau Pinang as a case study network. Grid-connected PV systems has a solar panels that produced a power needed in the day time, however the electricity supplied ongoing by distribution network operator during day night or whenever the solar panels produced low electricity because changes of weather (cloudy or rainy day). The case study network was selected because of a fault frequently occur and make the system unstable. The functionality of the case study network has been tested and troubleshooting has been carried out to identify the cause of the problems. Troubleshooting process had been done on the DC and AC side of the system by creating a troubleshooting table. The DC side of the system free from a fault, as proved by all the equipment in a good condition and PV array able to produce desired output voltage. The fault was occurred in the AC side of the system. The inverter has failed to produce desired output.
In the field of photovoltaic, the last few years have been very hotly discussed and researched as a new renewable source to produce electricity that cannot be exhausted. In the development effort there must be some problems arising from the existence of a new system. As with open circuit and short circuit interference. Therefore, The Identification of Open Circuit and Short Circuit Interference in Photovoltaic Array Installation with MPPT Based Artificial Neural Network is present to solve the problem. For identification of the location of the disruption is carried out on each photovoltaic string by knowing the voltage and current when there is an open circuit or short circuit interference, as well as the output power of the MPPT is used to determine the type of interference that occurs. Identification of interference using the Artificial Neural Network method with the purpose of this system can find out the location of interference and the type of open circuit or short circuit interference in photovoltaic array installations with MPPT. So that it is easy to know the location of the disturbance that is useful to maximize handling quickly and precisely. Keywords: Photovoltaic array, open circuit, short circuit, MPPT, Artificial Neural Network ABSTRAK Dalam bidang photovoltaic, beberapa tahun terakhir sangat hangat menjadi perbincangan dan penelitian sebagai sumber baru terbarukan untuk menghasilkan energi listrik yang tidak bisa habis. Dalam upaya pengembangnnya pasti ada beberapa permasalahan yang timbul dari adanya sistem baru. Seperti halnya adanya gangguan open circuit dan short circuit. Maka dari itu, Identifikasi Gangguan Open Circuit dan Short Circuit pada Instalasi Photovoltaic Array dengan MPPT Berbasis Artificial Neural Network hadir untuk menyelesaikan masalah tersebut. Untuk identifikasi lokasi gangguan dilakukan pada setiap string photovoltaic dengan mengetahui tegangan dan arus ketika terjadi gangguan open circuit maupun short circuit, serta daya keluaran dari MPPT digunakan untuk mengetahui jenis gangguan yang terjadi. Identifikasi gangguan menggunakan metode Artificial Neural Network dengan tujuan sistem ini dapat mengetahui lokasi gangguan dan jenis gangguan open circuit atau short circuit pada instalasi photovoltaic array dengan MPPT. Sehingga memudahkan untuk mengetahui lokasi gangguan yang berguna untuk memaksimalkan penanganan secara cepat dan tepat. Kata kunci: Photovoltaic array, open circuit, short circuit, MPPT, Artificial Neural Network
Photovoltaic (PV) arrays do not have moving parts. So, these require comparatively less maintenance. However, PV arrays operate under outdoor conditions in severe environment and lead to undergo different faults. Therefore, PV arrays’ fault diagnosis is necessary to make the PV energy systems more reliable. Due to varying environmental conditions and nonlinear PV characteristics, different artificial neural networks-based fault diagnosis has been proposed. But there are some concerns; e.g., fault diagnosis models are limited for mountainous region, and fault history is difficult to obtain using experimental analysis under outdoor condition. To address these concerns, this study proposes a new fault diagnostic techniques of PV module using extreme learning machine and multilayer feedforward neural network with Levenberg–Marquardt algorithm. For this, an experimental database of solar radiation, air and back surface module temperatures and electrical parameters of PV module are created by developing an experimental setup. This work is suitable for PV applications and researchers to estimate PV parameters for condition monitoring and would be useful for prior fault analysis of the PV module.KeywordsELMRBFNNLMPVFault
Full-text available
On the one end, humans are struggling to reduce carbon footprints, while on the other, energy demand is increasing every day. Humans are looking for renewable energy sources to handle both problems. Static as well as dynamic systems are being built on the principle of self-sufficiency. Moreover, a realistic estimation of environmental parameters is vital for both ground-based applications and space-based applications. A realistic estimate of environmental parameters is crucial in the design and development of aerospace systems and other ground structures and systems. The chapter describes a novel and robust approach for estimating power and energy estimation and other environmental parameters. It starts with describing the environment module in which modeling of operational parameters, viz., temperature, pressure, and ambient wind speed, is explained. The environment module consists of models for atmosphere, wind, and solar radiation. A robust numerical-based method to calculate total solar energy generation from any shape is described. Operating temperature is vital to solar array performance. Therefore, effect of operating temperature on solar efficiency is also discussed at the end.KeywordsSolar energyWind modelHWM14
Fault diagnosis is crucial for photovoltaic (PV) power generation, but the output uncertainty characteristics of PV arrays caused by different failures and their fluctuations make them facing new challenges. The parameter estimation (PE) method is widely used for uncertainty analysis, but there exist big differences between the PE results and the real output distributions. To solve this problem, this paper proposes a method for acquiring the fault diagnosis threshold based on non-parametric kernel density estimation (NKDE). First, the distribution characteristics of PV arrays output are statistically analysed, it is found that current and power are mainly affected by the solar irradiance, resulting in strong volatility and uncertainty, which makes it hard to get the threshold for fault diagnosis, thus we propose new three status indicators to finish it. Then, the probability models of the three indicators are built based on the kernel density estimation (KDE) method, by assigning the confidence values of the models, the fault diagnosis threshold intervals can be obtained. Verification shows that NKDE method performed better than traditional PE method in fitting the distribution of the PV arrays output, it does not need prior knowledge of the probability density function. And the proposed fault diagnosis method proves it is feasible to apply the uncertainty analysis method to PV array fault diagnosis. The paper provides a new idea for setting the dynamic threshold for PVarray fault diagnosis.
Full-text available
In this work we present a faults detection method for photovoltaic systems (PVS). This method is based on the calculation of sets of parameters of a PV module in different operating conditions, by means of a Neuro-Fuzzy approach. The PV system status is determined by evaluation and comparison of norms based on the aforementioned parameters, with threshold values. This intelligent system developed in Matlab&Simulink environment, consists on the study of the crucial information that the six parameters in normal and faulty condition contain. They are calculated using the I-V curves and synthesized by “hybrid” models. Results show that the diagnosis system is able to discern between normal and faulty operation conditions and with the same defective existence of noise and disturbances.
Full-text available
In this work we present a new procedure for automatic fault detection in grid connected photovoltaic (PV) systems. This method is based on the evaluation of new current and voltage indicators. Thresholds for these indicators are defined taking into account the PV system configuration: number of PV modules included and series and parallel interconnection to form the array. The procedure to calculate the thresholds that allow the identification of the faults is described. A simulation study was carried out to verify the evaluation of current and voltage indicators and their corresponding thresholds for a set of PV systems with different sizes and different configurations of interconnection of PV modules. The developed method was experimentally validated and has demonstrated its effectiveness in the detection of main faults present in grid connected applications. The computational analysis has been reduced and the number of monitoring sensors minimized. The fault detection procedure can be integrated into the inverter without using simulation software or additional external hardware.
Full-text available
In this work, an intelligent system for automatic detection of fault in PV fields is proposed. This system is based on a Takagi-Sugeno-Kahn Fuzzy Rule-Based System (TSK-FRBS), which provides an estimation of the instant power production of the PV field in normal functioning, i.e, when no faults occur. Then, the estimated power is compared with the real power and an alarm signal is generated if the difference between powers overcomes a threshold. The TSK-FRBS has been trained using data collected from a PV plant simulator, during normal functioning. Preliminary tests were carried out in a simulated framework, by reproducing both normal and fault conditions. Results show that the system can recognize more than 90% of fault conditions, even when noisy data are introduced.
This work proposes a novel fault diagnostic technique for photovoltaic systems based on Artificial Neural Networks (ANN). For a given set of working conditions - solar irradiance and photovoltaic (PV) module's temperature - a number of attributes such as current, voltage, and number of peaks in the current–voltage (I–V) characteristics of the PV strings are calculated using a simulation model. The simulated attributes are then compared with the ones obtained from the field measurements, leading to the identification of possible faulty operating conditions. Two different algorithms are then developed in order to isolate and identify eight different types of faults. The method has been validated using an experimental database of climatic and electrical parameters from a PV string installed at the Renewable Energy Laboratory (REL) of the University of Jijel (Algeria). The obtained results show that the proposed technique can accurately detect and classify the different faults occurring in a PV array. This work also shows the implementation of the developed method into a Field Programmable Gate Array (FPGA) using a Xilinx System Generator (XSG) and an Integrated Software Environment (ISE).
A new intelligent method is proposed to detect faults in the photovoltaic (PV) array. Usually, there is an obvious temperature difference between the fault PV module and the normal PV module. So, the temperature information of the PV modules is utilized to locate the fault in the PV array firstly. Then, the Artificial Neural Network (ANN) is applied to diagnosis the type of the fault. The current of maximum power point (I mpp), the voltage of maximum power point (V mpp) and the temperature of the PV modules are input parameters of the ANN. The output of the ANNunit is the result of the fault detection. Basic tests have been carried out in the simulated environment under both normal and fault conditions. The simulation results show that the outputs of the ANN are almost consistent with the expected value. It can be verified that the proposed method based on ANN can not only find the location of the fault but also determine the type of the fault.
The monitoring of photovoltaic (PV) systems is important for the optimization of their efficiency. In this paper, a low-cost smart multisensor architecture equipped with voltage, current, irradiance, temperature, and inertial sensors, for the monitoring (at the panel level) of a PV system, is presented with the aim of detecting the causes of efficiency losses. The system is based on a Wireless Sensor Networks with sensing nodes installed on each PV panel. The acquired data are then transferred to a service center where dedicated paradigms continuously perform the assessment of electrical efficiency as well the estimation of correlated causes, at the single panel level. In this paper, the detection of critical faults (temporary and permanent shadowing, dirtying, and anomalous aging) is addressed. The methodology adopted to estimate efficiency losses and related causes is based on the comparison between the measured efficiency of each PV panel and the nominal one estimated in the real operating conditions. Moreover, the anomalous aging estimation is based on the five parameter model approach that exploits a dedicated minimization paradigm to analyze the mismatch between the nominal current–voltage model of the PV panel and the measured one. The main advantage of the proposed approach is the continuous monitoring of PV plants and the assessment of possible causes of power inefficiency at the PV panel level, allowing for the implementation of a really efficient distributed fault diagnosis system. The experimental results are presented along with the analysis of the uncertainty affecting the measurement system.
In this work we present a faults detection method for photovoltaic systems (PVS). This method is based on the calculation of sets of parameters of a PV module in different operating conditions, by means of a Neuro-Fuzzy approach. The PV system status is determined by evaluation and comparison of norms based on the aforementioned parameters, with threshold values. This intelligent system developed in Matlab&Simulink environment, consists on the study of the crucial information that the six parameters in normal and faulty condition contain. They are calculated using the I-V curves and synthesized by “hybrid” models. Results show that the diagnosis system is able to discern between normal and faulty operation conditions and with the same defective existence of noise and disturbances.
Conference Paper
High penetration of photovoltaic (PV) systems is expected to play important roles as power generation source in the near future. One of the typical deployments of PV systems is without supervisory mechanisms to monitor the physical conditions of cells or modules. In the longer term operation, the cells or modules may undergo fault conditions since they are exposure to the environment. Manually module checking is not recommended in this case because of time-consuming, less accuracy and potentially danger to the operator. Therefore, provision of early automatic diagnosis technique with quick and efficient responses is highly necessary. Since high accuracy is the important issue in the diagnosis problems, the paper present fault diagnosis method using three-layered artificial neural network. A single artificial neural network (ANN) is not suitable to provide precise solution for this fault identification. Therefore, several ANNs are developed, then automatic control based module voltage terminal is established. The proposed method is simple and accurate to detect the exact location of short-circuit condition of PV modules in array.
Two methods for the fault location in PV module string were experimentally studied. One was the earth capacitance measurement (ECM) and the other was the time-domain reflectometry (TDR). By ECM, the disconnection position in the string was estimated by the earth capacitance value without the effects of the irradiance change, and the estimation error was small enough to determine the disconnection position in actual repair/maintenance operation. On the other hand, TDR could detect the degradation (series resistance increase) and the positions in the string by the change of response waveform.
It is reported that the volume of an estimated PV system installations in Japan must be set at about 4.82 [GW] up to 2010. As a result, it seems that PV systems must spread in the future in a general household, and therefore the maintenance and management of PV systems must become important keeping to the normal output performance of a PV system. However, it will be very difficult to locate the lowering factors to affect to output performance of the PV system installed in a residential rooftop. Besides, even if a cause of the output lowering of the PV system was found more, it will be very difficult to remove these. The authors paid attention to that shape of an I-V characteristic of a PV system changed by the output lowering caused by loss factors such as deterioration of a PV module, a shadow, and so on, and study the method to simply and automatically evaluate the output lowering of a PV system. In this paper, the (dI/dV)-V characteristic to be obtained from the I-V characteristic of a PV array is adopted as the standard characteristic for the automatic analysis. The (dI/dV)-V characteristic was simulated with an abnormal I-V characteristic of PV array covered in a shadow partially. A performance fall of PV array to be caused by a partial shadow is evaluated by an appearance of a peak of the (dI/dV)-V characteristic, and an appearance position of this peak changes by a condition of a shadow. From these results, it became clear that an appearance of a peak of a (dI/dV)-V characteristic must be means to be effective to diagnose the output lowering of a PV system