Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
7 results
Search Results
Item Comparative analysis of different machine learning techniques for condition monitoring of capacitors in a SEPIC converter(Institute of Electrical and Electronics Engineers Inc., 2022) RAJENDRAN, S.; Jena, D.; Diaz-D, M.; Devi, V.S.K.An efficient condition monitoring technique is essential for power converters to avoid unscheduled maintenance. In this work, the condition monitoring of capacitors in a single-ended primary inductance converter (SEPIC) is proposed based on the following machine learning classifiers: K nearest neighbor, support vector machine, back propagation neural network, Naive Bayes, and deep neural network. The feature of the machine learning algorithms is extracted by three node voltages such as voltage across $C$ 1,C2, and load. These features are utilized for training the algorithms. Moreover, the effectiveness of the different classifies are evaluated by considering the accuracy and area under the curve. Further, each algorithm is trained with a different percentage of a dataset. Finally, a comparative study has been made between the algorithms, and the results exhibit that the deep neural network performs better classification than other algorithms. © 2022 IEEE.Item Machine learning based condition monitoring of a DC-link capacitor in a Back-to-Back converter(Institute of Electrical and Electronics Engineers Inc., 2022) RAJENDRAN, S.; Jena, D.; Diaz-D, M.; Devi, V.S.K.The utilization of power electronic converters has increased, and the significance of continuous operation is essential in various applications. Therefore, proper condition monitoring (CM) is vital for power converters to eradicate unpredictable maintenance. However, the existing CM techniques may require additional sensors or injection of controlled voltage to the converters. The following machine learning algorithms, such as a K-nearest neighbors (KNN), Support Vector Machine (SVM), and Naive Bayes (NB), have been proposed to monitor the condition of the dc-link capacitor in a Back-to-Back (BTB) converter. The dc-link voltage is measured, and a wavelet decomposition is employed for the feature extraction. Moreover, the performance index evaluates the efficacy of the different classifiers. Further, different datasets have been considered for the evaluation of the classifiers. From this analysis, it is found that the SVM classifier performs better than others. © 2022 IEEE.Item Complementary Terminal Sliding Mode Control for Variable Speed Wind Turbine(Institute of Electrical and Electronics Engineers Inc., 2023) RAJENDRAN, S.; Jena, D.; Diaz-D, M.The reduction in transient loads on the drive train influences the life span of the wind turbine when designing the controller for power extraction. In wind turbines, compromises between the efficiency of power extraction and the load level on the drive train have become key issues. Conventional control techniques enhanced energy extraction at the cost of a higher transient load on the drive train. Therefore, this work proposes the complementary terminal sliding mode controller for energy extraction whilst reducing the drive train load. A 600 kW FAST simulator is utilised to validate the performance of the proposed and conventional controllers. Finally, a detailed investigation has been conducted based on energy extraction and mitigation of transient loads under various turbulence models and mean wind speeds. © 2023 IEEE.Item Wind Turbine Emulators—A Review(Multidisciplinary Digital Publishing Institute (MDPI), 2023) RAJENDRAN, S.; Diaz-D, M.; Devi, V.S.K.; Jena, D.; Travieso-Torres, J.C.; Rodríguez, J.Renewable energy sources have become a significant alternative energy source due to the continuing depletion of conventional energy sources and fluctuation in fuel costs. Currently, wind energy is the foremost among all other renewable energy sources. However, modeling and analyzing industrial wind turbines is complex as the wind turbine power ratio and size have steadily increased. Undoubtedly, industrial wind turbines are huge and challenging to keep in research labs; simultaneously, exploring the controller/power converter performance is practically impossible. Therefore, to overcome the above drawbacks, wind turbine emulators have been developed to achieve the static and dynamic characteristics of wind energy conversion systems. This paper aims to present a comprehensive review of the different wind turbine emulators available in the literature. In addition, the implementation of real-time emulators is classified according to the structure and approaches. Furthermore, an extensive analysis of the emulators was presented based on the significant parameters utilized for the real-time wind turbine emulators. Finally, this review analyzes the different emulator topologies according to cost, accuracy, complexity, and hardware implementation. © 2023 by the authors.Item Condition Monitoring of Submodule Capacitors in Modular Multilevel Converters—A Review(Elsevier Ltd, 2025) Saravanakumar, R.; Sivakumar, N.; Devi, V.S.K.; Shanthini, C.; Jena, D.; Ibaceta, E.; Diaz-D, M.; Rodríguez, J.Modular Multilevel Converters are highly promising power converter technologies used in high-voltage and high-power applications. The applications of modular multilevel converters are being increased in various industrial and renewable energy sectors due to their superior performance and efficiency. The modular multilevel converters contain multiple submodule capacitors, and these capacitors are the fragile components. The operating conditions and performance of these capacitors directly influence the system's reliability and operation. Hence, condition monitoring schemes are essential for submodule capacitors to ensure and enhance the modular multilevel converters operation which consequently reduces unscheduled maintenance. This article provides a detailed review and comprehensive analysis of condition monitoring schemes for submodule capacitors in modular multilevel converters. The review classifies the existing condition monitoring schemes into four major groups and thirteen subgroups and analyzes their methodologies using advantages and limitations of each scheme. Further, a critical analysis is presented with five significant parameters used to evaluate the condition monitoring schemes. The review highlighted the challenges related to condition monitoring accuracy, cost-effectiveness and system architecture that are to be studied in future. © 2025 Elsevier LtdItem Terminal Integral Synergetic Control for Wind Turbine at Region II Using a Two-Mass Model(Multidisciplinary Digital Publishing Institute (MDPI), 2023) RAJENDRAN, S.; Jena, D.; Diaz-D, M.; Rodríguez, J.Mechanical loads considerably impact wind turbine lifetime, and a reduction in this load is crucial while designing a controller for maximum power extraction at below-rated speed (region II). A trade-off between maximum energy extraction and minimum load on the drive train shaft is a big challenge. Some conventional controllers extract the maximum power with a cost of high fluctuations in the generator torque and transient load. Therefore, to overcome the above issues, this work proposes four different integral synergetic control schemes for a wind turbine at region II using a two-mass model with a wind speed estimator. In addition, the proposed controllers have been developed to enhance the maximum power extraction from the wind whilst reducing the control input and drive train oscillations. Moreover, a terminal manifold has been considered to improve the finite time convergence rate. The effectiveness of the proposed controllers is validated through a 600 kW Fatigue, Aerodynamics, Structures, and Turbulence simulator. Further, the proposed controllers were tested by different wind spectrums, such as Kaimal, Von Karman, Smooth-Terrain, and NWTCUP, with different turbulent intensities (10% and 20%). The overall performance of the proposed and conventional controller was examined with 24 different wind speed profiles. A detailed comparative analysis was carried out based on power extraction and reduction in mechanical loads. © 2023 by the authors.Item Design of modified complementary terminal sliding mode controller for wind turbine at region II using a two-mass model(Elsevier B.V., 2024) RAJENDRAN, S.; Jena, D.; Diaz-D, M.; Rodríguez, J.Mechanical loads impact the life span of a wind turbine; therefore, the reduction of transient loads in the drive train has gained more emphasis during the design of the controller for power extraction. The trade-off between power extraction and load reduction on the drive train has become a critical concern for wind turbines. Existing control approaches improve energy extraction and impose a more significant transient load on the drive train. Therefore, to address the above issue, a modified complementary terminal sliding mode controller is proposed in this study for wind turbines at below-rated wind speeds. The performance of both the proposed and existing controllers has been tested with a 600 kW FAST simulator. Moreover, each controller has been examined using different wind spectral models, such as Kaimal, Von Karman, Smooth-Terrain, and NWTCUP. The turbulent intensities of these models varied from 5% to 25%, and average wind speeds ranged from 7 m/s to 8.5 m/s. A dSPACE 1202 board was used to test the efficacy of the proposed controller in real-time. This analysis indicates that the proposed controller reduces the transient load by 11.98% and the control input by 9.57% compared to the complementary terminal sliding mode controller. Additionally, the proposed controller improves the energy capture by 1.18%. Finally, this analysis shows that the proposed approach can enhance overall performance and capture maximum power at below-rated wind speeds compared to existing control schemes. © 2024 The Authors