Jelena Loncarski

Dr. Jelena Loncarski

Politecnico di Bari - DEI
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2018
Verified
Conference Paper
Closed access
MPMarina Paolanti
Marina Paolanti
LRLuca Romeo
Luca Romeo
AFAndrea Felicetti
Andrea Felicetti
AMAdriano Mancini
Adriano Mancini
EFEmanuele Frontoni
Emanuele Frontoni
Jelena LoncarskiJelena Loncarski
Jelena Loncarski
Condition monitoring together with predictive maintenance of electric motors and other equipment used by the industry avoids severe economic losses resulting from unexpected motor failures and greatly improves the system reliability. This paper describes a Machine Learning architecture for Predictive Maintenance, based on Random Forest approach. The system was tested on a real industry example, by developing the data collection and data system analysis, applying the Machine Learning approach and comparing it to the simulation tool analysis. Data has been collected by various sensors, machine PLCs and communication protocols and made available to Data Analysis Tool on the Azure Cloud architecture. Preliminary results show a proper behavior of the approach on predicting different machine states with high accuracy.

17 October 2014 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Gabriele GrandiGabriele Grandi
Gabriele Grandi
Jelena LoncarskiJelena Loncarski
Jelena Loncarski
ODObrad Dordevic
Obrad Dordevic
Three-phase multilevel (ML) inverters are used in many medium- and high-power applications such as motor drives and grid-connected systems. Despite the fact that numerous pulsewidth modulation (PWM) techniques for ML inverters have been developed, the impact of these modulation schemes on the peak-to-peak output current ripple amplitude has not been addressed yet. In this paper, analysis and comparison of current ripple for two-level (2L) and three-level (3L) voltage source inverters are given. Reference is made to optimal and popular modulation, so-called centered PWM, easily obtained by both carrier-based modulation (phase disposition, with proper common-mode voltage injection) and space vector modulation (nearest three vectors). It is shown that the peak-to-peak current ripple amplitude in 3L inverters can be determined on the basis of the ripple in 2L inverters, obtaining the same results as by directly analyzing the output voltage waveforms of the 3L inverters. This procedure can be readily extended to higher level numbers. The proposed analytical developments are verified by both numerical simulations and experimental tests.

1 February 2020 in Expert Systems with Applications
Verified
Journal Article
Closed access
Luca RomeoLuca Romeo
Luca Romeo
Jelena LoncarskiJelena Loncarski
Jelena Loncarski
MPMarina Paolanti
Marina Paolanti
GBGianluca Bocchini
Gianluca Bocchini
AMAdriano Mancini
Adriano Mancini
Emanuele FrontoniEmanuele Frontoni
Emanuele Frontoni

1 June 2013
Verified
Conference Paper
Closed access
Gabriele GrandiGabriele Grandi
Gabriele Grandi
Jelena LoncarskiJelena Loncarski
Jelena Loncarski
Determination of current ripple in three-phase PWM voltage source inverters (VSI) is important for both design and control purposes, since this is the most popular conversion topology for energy conversion systems. In this paper the complete analysis of the peak-to-peak current ripple distribution over a fundamental period is given for three-phase VSIs. In particular, peak-to-peak current ripple amplitude is analytically determined as a function of the modulation index. Minimum, maximum, and average values are also emphasized. Although the reference is made to continuous symmetric PWM, being the most simple and effective solution to minimize the current ripple, the analysis could be easily extended to either discontinuous or unsymmetrical modulation, both carrier-based and space vector PWM. The analytical developments for all the different subcases are verified by numerical simulations.

1 June 2015
Verified
Conference Paper
Closed access
Sanjeevikumar PadmanabanSanjeevikumar Padmanaban
Sanjeevikumar Padmanaban
Gabriele GrandiGabriele Grandi
Gabriele Grandi
Patrick WheelerPatrick Wheeler
Patrick Wheeler
Frede BlaabjergFrede Blaabjerg
Frede Blaabjerg
Jelena LoncarskiJelena Loncarski
Jelena Loncarski
This paper presents the novel topology of Photo Voltaic (PV) power generation system with simple Maximum Power Point Tracking (MPPT) algorithm in voltage operating mode. Power circuit consists of high output voltage DC-DC boost converter which maximizes the output of PV panel. Usually traditional DC-DC boost converters are used for such application, but they are not the most suitable solution due to output limitation, lower efficiency and require more sensors with complex control algorithm. Further on, the effects of parasitic elements are suppressed, as well as the power transfer efficiency of DC-DC converters for PV integration. Hence, to overcome these difficulties this paper investigates a DC-DC boost converter together with the additional parasitic component within the circuit to provide high output voltages for maximizing the PV power generation. The proposed power system circuit substantially improves the high output-voltage by a simple MPPT closed loop proportional-integral (P-I) controller, and requires only two sensor for feedback needs. The complete numerical model of the converter circuit along with PV MPPT algorithm is developed in numerical simulation (Matlab/Simulink) software. A detailed performance analysis is carried out under both PV panel irradiation (high/low) and load regulation conditions. Numerical results obtained in this paper are in the agreement with the theoretical developments, proving the effectiveness of the proposed topology.

14 July 2018
Verified
Book Chapter
Closed access
PDF file
EFEmanuele Frontoni
Emanuele Frontoni
Jelena LoncarskiJelena Loncarski
Jelena Loncarski
Roberto PierdiccaRoberto Pierdicca
Roberto Pierdicca
MBMichele Bernardini
Michele Bernardini
MSMichele Sasso
Michele Sasso