Search

Photovoltaic arrays may suffer from a number of temporary and permanent faults. Partial shading and soiling belong to the former group, while cell cracking and delamination fall within the latter one. In these cases, the shape of the current vs voltage curve around the maximum power point shows features that are different from those ones of an array operating in normal conditions. The shape change should allow triggering, in case of a temporary fault, control actions that might improve the electrical power production. Instead, if the fault is permanent, the identification of the modified shape should activate a procedure for a more in-depth analysis of the problem and a maintenance action. In this paper, the conditions leading to a change in the array behavior during its delivering of the maximum power are examined. The change of curvature of the current vs voltage curve around its maximum power point is suitably detected to trigger the fault mitigation action. The feature is caught through an ensemble of artificial neural networks, which analyzes the current vs voltage curve and classifies the module as healthy or faulty. It is demonstrated that few samples around the maximum power point are required, this meaning that the proposed approach is compatible with the operation of any perturbative maximum power point tracking algorithm and its application does not lead to any power production drop. In addition, the approach does not require neither temperature nor irradiance measurements as inputs. The neural networks are trained through synthetic data, so that their application is not limited to arrays including a specific photovoltaic module. The method is also validated through experimental data. [Display omitted] • Some types of PV faults lead to a change of the shape of the I – V curve around the MPP. • An Artificial Neural Network catches this change to classify a curve as healthy or faulty. • Only few samples around the MPP are required without irradiance or temperature data. • The model is trained with synthetic data being not limited to a specific module. • Best trained neural networks can be combined into an ensemble to improve the results. [ABSTRACT FROM AUTHOR]

In this paper, a procedure aimed at the automatic extraction of the features from polymer electrolyte membrane fuel cell impedance spectra is proposed. An artificial neural network that is trained by exploiting the similarity learning concept has been used. The network learns the features of the impedance spectra and maps each of them into the embedding space by clustering them accurately and by emphasising differences among spectra corresponding to different faults. The siamese network structure is optimised and the quality of the learnt representation is evaluated by analysing the clusters obtained in the features space. The dataset of experimental spectra has been augmented in two different ways and the results are compared. The clustering quality of the proposed siamese network is compared with the one of other state of the art approaches. [Display omitted] • A Siamese Neural Network is used to analyse the impedance spectra of a PEM fuel cell. • The SNN is able to extract the features corresponding to each faulty condition. • Two different data augmentation approaches are used to train the SNN and their performance is analysed. • The approach is tested on a set of noisy impedance spectra. [ABSTRACT FROM AUTHOR]

Highlights: [•] Minimizing hydrogen consumption in fuel cell applications. [•] Perturbation strategy for optimization. [•] Virtual sensing of the oxygen excess ratio. [•] Hardware in the loop test of a FPGA controller. [ABSTRACT FROM AUTHOR]

[Display omitted] • A neural network is used to detect faults in photovoltaic modules. • According to the shape of the current vs voltage curve, the faults are classified. • The training uses synthetic curves and the test is performed also on experimental data. • The points are normalized and resampled radially to improve the results. • With two hidden layers of 100 neurons each, the hit rate reaches more than 98.5%. In this paper a model-based procedure for fault detection and diagnosis of photovoltaic modules is presented. A four-layered feedforward artificial neural network learns the correlation between the features of the current vs. voltage curve and the environmental variables, which are the irradiance and the temperature. This correlation describes the behavior of the module at normal conditions. Moreover, the effect of anomalous variation of some parameters is learnt and correlated to the shape of the same curve, thus associated to a specific failure mechanism and to some assigned ranges quantifying the fault severity. The neural network is trained by using synthetic curves simulated by employing the single diode model and some well assessed and validated translation formulae. The obtained results over the simulated set of curves with different failures allow to achieve a classification error lower than 1.5%. The proposed approach has been also validated for detecting anomalous increases of the series resistance in a large experimental set of curves; in this case, a classification error of 2.7% has been achieved. [ABSTRACT FROM AUTHOR]

• Parametric identification of a Fuel Cell stack based on the Interval Arithmetic. • Robustness with respect to the uncertainties affecting the EIS measurements. • Smart Branch and Bound algorithm for reducing computational burden and memory. • Suitable for the on line diagnosis of electrochemical systems as FC and batteries. In this paper, the identification of the equivalent circuit parameters of a polymer electrolyte fuel cell stack is performed for diagnostic and monitoring purposes. An interval arithmetic branch and bound method is developed for the identification of parameters of the Fouquet model, frequently used for fuel cell modeling in the frequency domain. The proposed method allows to bound each parameter by an interval of real values. It also provides the model sensitivity with respect to the parameters. The method is also able to account for uncertainties affecting the impedance measurements at the assigned frequency values. For the specific application to fuel cells, the approach overcomes the limitations, in terms of interval contraction capability, characterising standard interval analysis-based techniques. The features of the proposed approach, shown with various examples also involving experimental measurements, are useful in monitoring the stack performance, to the final aim of improving its lifetime, and ensuring the expected electrical power production. The proposed results allow to envisage an application of the method also in real time conditions, when the fuel cell model parametric identification has to be run by using an embedded system instead of a personal computer. [ABSTRACT FROM AUTHOR]

[Display omitted] • Novel method to identify the SDM parameters and operating conditions of a PV module. • It does not require irradiance nor temperature, but identifies both accurately. • The method can be applied using only a small portion of the curve around the MPP. • Fort the first time, a comparison of various fitting approaches is presented. • It is proven that fitting approach is a factor to be considered for I – V curve fitting. One solution for online condition monitoring of photovoltaic (PV) modules is to identify single-diode model parameter values from measured current–voltage (I – V) curves. By this way, use of expensive thermal cameras and radiometric sensors utilized in traditional monitoring methods can be avoided. Unfortunately, most of the parameter identification methods require measurements of the operating conditions, i.e., irradiance and temperature. This article proposes a novel procedure for identification of the single-diode model parameter values along with the operating irradiance and temperature values from measured I – V curves without needing any other measurement. The only inputs of the proposed procedure are the I – V curve measurements at the actual operating conditions together with the parameter values of the module model in standard test conditions. The proposed procedure is experimentally validated using I – V curves of three PV module types measured from two different locations. Both the whole I – V curves or only a part of them, in a limited voltage range, are considered. Moreover, I – V curve measurements with an emulated increase of the series resistance are used to demonstrate the correctness of the identified series resistance values. It is shown that the procedure identifies the operating irradiance and temperature with high accuracy even during sharp irradiance transitions and low irradiance conditions and identifies series and shunt resistances very reliably under nearly constant high irradiance conditions. Moreover, for the first time, a comprehensive comparison of various fitting approaches based on root-mean-square error (RMSE) minimization, including two novel approaches, is presented. The results show that the different fitting approaches based on RMSE minimization affect the accuracy of the parameters identification in a different way, this meaning that the used fitting approach is a factor that should be considered when implementing model parameter identification by curve fitting. [ABSTRACT FROM AUTHOR]

The performance of four thin-film photovoltaic modules is analyzed after an initial stabilization period and a subsequent outdoor exposition. The seasonal variations and the degradation rates of a single-junction hydrogenated amorphous silicon (a-Si:H) module, a tandem amorphous microcrystalline Silicon (a-Si/ μ c-Si) module, a heterostructure cadmium sulfide-cadmium telluride (CdS/CdTe) module and a copper indium gallium selenide (CIGS) are examined and correlated to spectral changes. The I–V curves have been measured every 5 min; the electrical parameters and parasitic resistances have been identified. By exploiting a number of experimental measurements acquired within a narrow interval of irradiance and cell temperature, a novel mathematical model has been developed and fitted: it considers a stationary seasonal variation component and a linear long-term degradation component. The results show annual power degradation rates of 4.0% for the a-Si:H module, 3.4% for the a-Si/ μ c-Si and 3.5% for the CdS/CdTe, whereas for the CIGS module the annual degradation is not significant, i.e. 0.2%. [Display omitted] [ABSTRACT FROM AUTHOR]

Highlights: [•] The steady state MPPT efficiency of the P&O algorithm has been analysed and the optimal operating conditions have been identified. [•] An improvement of the P&O algorithm based on a two steps perturbation has been proposed. [•] The simplicity and the computational burden of the classical P&O algorithm have been preserved in the proposed algorithm. [•] The quantization errors and numerical approximations introduced by the digital implementation have been properly compensated. [•] The new algorithm is suitable for an implementation on cheap digital controllers. [Copyright &y& Elsevier]

In this paper a computationally efficient optimization approach to the parametric identification of a fuel cell equivalent circuit model is presented. It is based on the inverse model and on machine learning regressions. During the training phase, the inverse model is built numerically by means of advanced regression approaches, i.e., the support vector machine regression, the least squares support vector machine regression and the Gaussian process regression. The training set is synthetically generated to the aim of exploring the parameter space and to characterize different stack operating conditions, including normal and faulty ones. The accuracy of the considered approaches is investigated by employing a test set including many experimental data, consisting of impedance spectra measured through the electrochemical impedance spectroscopy and referring to very different stack operating conditions. The results show that all the considered machine learning methods allow to identify the parameters of the fuel cell model with a low computational burden, so that they fit with the hardware resources of low cost embedded processors. This feature allows to envisage that the proposed approaches are good candidates for a model-based on-line diagnosis of fuel cell stacks. [Display omitted] • Parameter identification of equivalent circuit model performed through Inverse Model. • Parameter search space is first constrained in feasibility regions. • Inverse Models built through GPR, SVM and LS-SVM machine learning regression models. • The identification results are shown for both synthetic and experimental data. • Performance and Resource Usage of the embedded implementation are explored. [ABSTRACT FROM AUTHOR]

Abstract: In this paper a current controller is used to reject the 100-Hz oscillation of the voltage of the photovoltaic field taking place in any grid connected system. With respect to the classical linear voltage control the current-based sliding-mode approach ensures a wider regulation band but, unfortunately, in presence of a fast irradiance variation the sliding conditions might be violated, so that the operating point, which should be the maximum power point, might not be the expected one. In order to prevent such a drawback, an appropriate voltage compensation loop is used to interface the current-based sliding mode with the Maximum Power Point Tracking algorithm. Simulation and experimental results confirm the goodness of the proposed algorithm. [Copyright &y& Elsevier]