A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks

Chine, W.; Mellit, A.; Lughi, Vanni; Malek, A.; Sulligoi, Giorgio; Pavan, Alessandro

doi:10.1016/j.renene.2016.01.036

Cited by 431 publications

(219 citation statements)

References 33 publications

Supporting

Mentioning

217

Contrasting

Unclassified

Order By: Relevance

“…This method was proposed by [21] and used in [27 and 28] for the estimation of R s . There are two options to calculate Q (9 & 10).…”

Section: Methodsmentioning

confidence: 99%

“…where K 1 is the ratio between I mpp and I sc and it is assumed as constant value of 0.92 as described by [21].…”

Section: Methodsmentioning

confidence: 99%

“…Furthermore, machine learning techniques have been also applied in PV systems for fault detection purposes. ANN network was used by [21] for detection multiple faults in a PV system such as faulty PV modules and faulty bypass diodes. S. Silvestre et al [22] proposed a new procedure for fault detection in PV systems which is based on the analysis of the voltage and current ratios for the entire GCPV plant.…”

Section: A C C E P T E D Accepted Manuscriptmentioning

confidence: 99%

See 2 more Smart Citations

Seven indicators variations for multiple PV array configurations under partial shading and faulty PV conditions

et al. 2017

View full text Add to dashboard Cite

The goal of this paper is to model, compare and analyze the performance of multiple photovoltaic (PV) array configurations under various partial shading and faulty PV conditions. For this purpose, a multiple PV array configurations including series (S), parallel (P), series-parallel (SP), total-cross-tied (TCT) and bridge-linked (BL) are carried out under several partial shading conditions such as, increase or decrease in the partial shading on a row of PV modules and increase or decrease in the partial shading on a column of PV modules. Additionally, in order to test the performance of each PV configuration under faulty PV conditions, from 1 to 6 Faulty PV modules have been disconnected in each PV array configuration. Several indicators such as short circuit current (I sc ), current at maximum power point (I mpp ), open circuit voltage (V oc ), voltage at maximum power point (V mpp ), series resistance (R s ), fill factor (FF) and thermal voltage (V te ) have been used to compare the obtained results from each partial shading and PV faulty condition applied to the PV system. MATLAB/Simulink software is used to perform the simulation and the analysis for each examined PV array configuration.

show abstract

“…This method was proposed by [21] and used in [27 and 28] for the estimation of R s . There are two options to calculate Q (9 & 10).…”

Section: Methodsmentioning

confidence: 99%

“…where K 1 is the ratio between I mpp and I sc and it is assumed as constant value of 0.92 as described by [21].…”

Section: Methodsmentioning

confidence: 99%

Section: A C C E P T E D Accepted Manuscriptmentioning

confidence: 99%

See 1 more Smart Citation

Seven indicators variations for multiple PV array configurations under partial shading and faulty PV conditions

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Huge research efforts have been undertaken worldwide to develop incipient fault (before the actual occurrence of faults) diagnostic techniques. Neural network (NN) or known as artificial neural network (ANN) is a tool that plays an important role in developing online and offline diagnostic tools for motors, generators, transmission lines, cables, and transformers [32][33][34][35][36][37]. A mathematical model of an induction machine with stator inter-turn fault has been derived based on winding function theory [8].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Stator Inter-Turn Fault Diagnosis Tool for Induction Motors

2018

View full text Add to dashboard Cite

Induction motors constitute the largest proportion of motors in industry. This type of motor experiences different types of failures, such as broken bars, eccentricity, and inter-turn failure. Stator winding faults account for approximately 36% of these failures. As such, condition monitoring is used to protect motors from sudden breakdowns. This paper proposes the use of neural networks as an efficient diagnostic tool for estimating the percentage of stator winding shorted turns in three-phase induction motors. A MATLAB-based model was developed and simulated under different fault-load combination cases for different sizes of motors. The motor's developed electromechanical torque was selected as a fault indicator. For the design and training of the neural network, the mean, variance, max, min, and F120 time based on statistical and frequency-related features were found to be very distinct for correlating the captured electromechanical torque with its corresponding percentage of shorted turns. In the training phase of the neural network, five different motors were used and are referred to as seen motors. On the other hand, for testing the efficiency of the developed diagnostic tool, the electromechanical torque under different fault-load combination cases, previously never seen from the first five motors and those of two new motors (referred to as unseen), was used. Testing results revealed accuracy in the range of 88-99%.

show abstract

“…The fault detection algorithm can determine the location and the type of the faults in the DC-side of the GCPV system. Moreover, W. Chine et al [5] proposed a novel fault diagnosis technique that allows detecting multiple faults in the GCPV systems such as short circuit fault in PV module, bypass diodes failures and partial shading effect in group of cells equipped by a faulty bypass diodes.…”

Section: Introductionmentioning

confidence: 99%

Fault detection algorithm for multiple GCPV array configurations

Dhimish

Holmes

Dales

et al. 2017

2017 IEEE Manchester PowerTech

View full text Add to dashboard Cite

Abstract-In this paper, a fault detection algorithm for multiple grid-connected photovoltaic (GCPV) array configurations is introduced. For a given set of conditions such as solar irradiance and photovoltaic module temperature, a number of attributes such as power, voltage and current are calculated using a mathematical simulation model. Virtual instrumentation (VI) LabVIEW software is used to monitor the performance of the GCPV system and to simulate the theoretical I-V and P-V curves of the examined system. The fault detection algorithm is evaluated on multiple GCPV array configurations such as series, parallel and series-parallel array configuration. The fault detection algorithm has been validated using 1.98 kWp GCPV system installed at the University of Huddersfield. The results indicates that the algorithm is capable to detect multiple faults in the examined GCPV plant and can therefore be used in large GCPV installations.Index Terms-Photovoltaic (PV); Fault detection algorithm; GCPV multiple array configurations; VI LabVIEW software.

show abstract

A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks

Cited by 431 publications

References 33 publications

Seven indicators variations for multiple PV array configurations under partial shading and faulty PV conditions

Seven indicators variations for multiple PV array configurations under partial shading and faulty PV conditions

An Efficient Stator Inter-Turn Fault Diagnosis Tool for Induction Motors

Fault detection algorithm for multiple GCPV array configurations

Contact Info

Product

Resources

About