NITIN KESHAORAO DHOTE

@stvincentngp.edu.in

Associate Professor & Head, Electrical Engineering
St. Vincent Pallotti College of Engineering & Technology

NITIN KESHAORAO DHOTE


                  Download Compact PDF  
https://researchid.co/nitindhote

RESEARCH INTERESTS

Power System protection
Dissolved Gas Analysis
Electrical Power System
Renewable Energy Sources
22

Scopus Publications

Scopus Publications

  • DGA-Driven Transformer Fault Prognosis Using Reinforcement Learning and Predictive Uncertainty Estimation
    Swati R. Ghutke, Nitin K. Dhote, Swapna M Choudhary
    2026 International Conference on Communication Computing and Emerging Technologies Ic3et 2026, 2026
    Reliable transformer condition-monitoring is essential for ensuring the uninterrupted power system operation, and Dissolved Gas Analysis (DGA) which remains the most widely used diagnostic technique. However, traditional ratio-based methods, and static machine-learning models focuses primarily on fault diagnosis rather than predicting the future fault evolution, by limiting their usefulness for the proactive maintenance. This study proposes a reinforcement learning (RL) driven framework for transformer fault prognosis that learns temporal DGA progression, forecasts multi-step gas trajectories, and estimates predictive uncertainty to improve decision confidence. A MATLAB based thermal, and DGA simulation environment has been developed to generate realistic fault progression scenarios, including PD, D1/D2, and T1–T3 faults. The RL model achieves superior forecasting accuracy with MAPE values of 4.8% for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{H}_{2}, 5.1 \%$</tex> for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{CH}_{4}$</tex>, and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$6.4\%$</tex> for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{C}_{2} \mathrm{H}_{4}$</tex>, by outperforming LSTM, and ANN baselines by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$30-60 \%$</tex>. The framework provides early warning signals of an average of 6.5 days, before critical fault transitions, which is compared to 3.8 days for LSTM, and the nearly zero for ratio-based methods. Predictive uncertainty estimation by using Monte-Carlo dropout, enhances the operational trust by revealing confidence intervals that widen before the abnormal transitions. Overall, the results demonstrate that the proposed RL-based approach enables reliable, forward-looking transformer fault prognosis, as well as constitutes a significant advancement beyond the existing diagnostic techniques.
  • Adaptive and Interpretable MPPT Framework for Photovoltaic Systems under Partial Shading using Integrated AI Modules
    Manoj B Maurya, Nitin K Dhote, Swapna Choudhary, Kirti Vaidya
    Ssrg International Journal of Electrical and Electronics Engineering, 2025
    Long-term widespread research has been undertaken on the need for strong and adaptable Maximum Power Point Tracking (MPPT) strategies for Photovoltaic (PV) systems owing to the far-reaching impact of PSCs, which seriously affects energy harvesting efficiency. Therefore, over and above substantial delays in the classic MPPT algorithms--that is, Perturb &amp; Observe or Incremental Conductance–are largely considered classical MPPT methods, and their effectiveness becomes further limited owing to false convergence, slow adaptation, and limited generalization under dynamically changing shading patterns, resulting in sometimes low performance of such algorithms when enforced in the real-world environment. This paper proposes an integrated AI-powered MPPT framework created to tackle real-time power optimization issues owing to PSCs. The system comprises five tightly coupled modules: Contextual Hierarchical Transfer Graph Embedding (CHTGE) is implemented for transfer learning for a variety of environmental conditions by policy graphs on the premise of shading history combined with weather context. The role of Spatio-Temporal Feature Attention-based Indexing (STFAI) is to facilitate the detection of transient phenomena through the utilization of attention maps that are temporally aligned and derived from real-time multimodal sensor data. In the tertiary module, Differential Contextual Residual Optimization (DCRO) rectifies inaccuracies and achieves rapid stabilization through the application of residual corrections in a highly fluctuating environment. The output obtained using conventional Maximum Power Point Tracking (MPPT) methodologies is upgraded with multi-agent decision fusion with quantum-inspired adaptive logic (MADF-QAL). The Evolution-based Causal Disentanglement Networks (ECDN) provide fault localization and explainability through latent representation. There is an estimated improvement in the system performance by 28% in sensing the partial shading patterns, and a 33% reduction in the number of false triggers. Also, approximately 2.3 times quicker recovery from deviation in power, and 41% improvement in the decision-making process, and hence faster fault analysis. The proposed work suggests a framework of interpretable, resilient, and intelligent MPPT control under real-world operating scenarios.
  • Performance analysis of conventional multilevel inverter driven PMSM drive in EV applications
    Rakesh G. Shriwastava, Pravin B. Pokle, Ajay M. Mendhe, Nitin Dhote, Rajendra M. Rewatkar, Rahul Mapari, Ranjit Dhunde, Hemant R. Bhagat Patil, Ramesh Pawase
    International Journal of Applied Power Engineering, 2025
    This paper describes the simulation and hardware analysis of a two-level inverter-driven permanent magnet synchronous motor (PMSM) drive in EV applications. The design of various sections of PMSM Drive is discussed in detail. This proposed work is based on the voltage source converter (VSC) fed four-pole, 373 W. This paper highlights the design and implementation using a microcontroller of (PMSM) drive for various operating conditions. The experimental results show that the control and power circuit used in the design can achieve excellent and consistent speed performance. The performance along with test results of the speed and load variation of the PMSM drive is studied for steady-state conditions. The performance of the motor has been checked by increasing the inverter frequency with the speed of the motor and also keeping the frequency remains constant by varying the load and speed. Hardware analysis indicates the improved performance of the motor and the drive. It has good speed and torque responses and is suitable for EPS applications.
  • DTC analysis of DCMLI driven PMSM-SVM drive
    Rakesh G. Shriwastava, Pravin B. Pokle, Ajay M. Mendhe, Nitin Dhote, Rajendra M. Rewatkar, Rahul Mapari, Ranjit Dhunde, Hemant R. Bhagat Patil, Ramesh Pawase
    International Journal of Applied Power Engineering, 2025
    The paper focuses on a comparative analysis of direct torque control (DTC) space vector modulation (SVM) based permanent magnet synchronous motor (PMSM) drive. This comparative analysis is based on a conventional inverter and a 3-level dual-cell modular multilevel inverter (DCMLI) using the SVM technique using MATLAB simulation. The present DTC-PMSM drive consists of flux and torque hysteresis comparators and has a problem of switching frequency and torque ripple. The problems are solved by using SVM to provide more inverter voltage and it compensates for torque and flux error in a DTC. A reference voltage space vector is calculated every time using the algorithm on the basic of torque error and stator flux angle. It was proposed to control torque, torque angle, and stator flux in DTC-PMSM. From the detailed comparison, the DTC-DCMLI PMSM drive has an exact solution of problem-solving of switching frequency and torque ripple due to less distorted output. Proposed drives can be applicable for hardware implementation in automotive applications.
  • Artificial Intelligence-Based Transient Stability Enhancement of STATCOM-Assisted Hybrid Renewable Energy System on IEEE Bus Network
    Bhishan Wadhai, Nitin Dhote, Mohan Lal Kolhe
    2025 IEEE 7th International Conference on Computing Communication and Automation Iccca 2025, 2025
    The incorporation of renewable energy resources such as photovoltaic (PV) and wind into power systems increases the necessity for advanced transient stability control strategies because these sources are inherently stochastic and nonlinear for different scenarios. Traditional methods for assessing and controlling stability typically use linearized models or fixed-parameter controllers along with rule-based schemes, which prove inadequate in dynamic fault situations and actually do not apprehend the complex interactions of renewable generators with grid components and power electronics-based devices like STATCOMs. Consequently, this work proposes a novel AI-based framework for transient stability analysis and improvement of a STATCOM integrated hybrid renewable energy system based on the IEEE 9-bus network. The proposed model incorporates five analytically rigorous and computationally innovative methods. First, a Dual-Stage Attention-based Graph Neural Network (DA-GNN) is implemented to accurately predict transient stability margins through the capturing of both temporal and spatial dynamics. Second, a Reinforcement Learning-based Dynamic STATCOM Control (RL-DSC) with event-triggered architecture ensures adaptive voltage regulation during disturbances. Third, a Physics-Guided Generative Adversarial Network (PG-GAN) generates physically consistent fault scenarios, expanding training datasets for better model generalization. Fourth, an Entropy-Guided Feature Pruning with Explainable AI (EGFP-XAI) technique improves interpretability and reduces computational complexity. Finally, a Hybrid Koopman Operator-AI Model for Modal Interaction Tracking (KAI-MIT) enables real-time tracking of inter-area oscillations and instability growth sets. This mechanism substantially improves prediction accuracy, control responsiveness and robustness of the transient stability techniques. The system’s performance thus includes a considerable margin prediction accuracy of 97.8% for stability, reduced voltage recovery time of 42%, and better detection of unstable modes, thus providing intelligent and scalable solutions to modern hybrid power systems.
  • Tractor with Green Charger Using Buck Zero Current Switching Converter for Agriculture
    Diksha Khare, Nitin Dhote, Swapna Choudhary
    2025 IEEE International Conference on Smart Power Energy Renewables and Transportation Spert 2025 Proceedings, 2025
    For the new generation with increasing demand for power supply, Hybrid renewable energy systems (HRES) are an essential and immediate solution. During the recent years, Renewable Energy technologies are going through constant advancement and hence offering a fair share in Power supply requirements of new generation. In this paper we have presented Hybrid powered model comprising a photovoltaic, a wind generator plus battery bank storage of power considering the uncertainty of weather conditions. DC-DC converter namely ZCS Buck Converter is supplied from this storage battery. This HRES topology supplies low voltage battery charger. Batteries play a significant role in day to day life, as a reliable energy source for storage systems, However, conventional battery chargers are typically bulky and experience significant power dissipation during the charging process, leading to poor efficiency. Therefore, selecting an appropriate method of charging is crucial to improve the efficiency of charging and prolong the overall lifespan of the battery. The duty ratio of the converter can control the operation of the Hybrid renewable energy systems HRES operation be and therefore can supply the variable DC load.
  • Measurement and intermittent performance analysis of 12-switch NPC inverter driven PMSM drive in electric vehicle application
    Rakesh Shriwastava, Sunildatta Kadlag, Ramesh Pawase, Nitin Dhote, Rajendra Rewatkar, Rahul Mapari, Ranjit Dhunde, Hemant R. Bhagat Patil
    International Journal of Vehicle Noise and Vibration, 2025
    This paper deals with the measurement and intermittent performance analysis of 12-switch NPC inverter driven PMSM drive in electric vehicle application. The objective of this paper is to demonstrate the multilevel inverter driven PMSM drive with carrier-based space vector modulation (CBSVM) strategy in MATLAB environment with reduction of total harmonic distortion and torque ripple. The method currently used for constant speed and torque is field oriented control (FOC) in permanent magnet synchronous motor (PMSM). The simulation results are presented based on inverter output and motor parameters such as stator and rotor current, speed and torque of PMSM. After validation of results, the proposed FOC-based 12-switch neutral point clamped inverter (TSNPCI) driven PMSM drive is found suitable for electric vehicles due to speed, torque response, better control performance, good dynamic response and lower costs. The hardware and simulation results are validated and matched for the effectiveness of the drive.
  • Detection of Plant Leaf Diseases Using Internet of Things and Machine Learning Based Drone System
    Swapna Choudhary, Nitin Dhote, Mohan Lal Kolhe
    Advances in Transdisciplinary Engineering, 2024
    With rapid improvement in technology, drones become one of the best fit for agriculture due to their various applications such as spraying pesticides and supervising the yield area of farms. A drone-based system can help in detecting the diseases before they spread to the whole farm. The use of the technology will improve the efficiency of the farming sector. The system is designed using the Internet of Things (IoT) with the help of the ESP32 Cam board, Machine Learning (ML) algorithm, and Google Workspace. ESP-32 Cam module captures the images of plants. Google Drive is used to store captured images. The machine learning algorithm is used to extract features from images and detect possible plant diseases. Workspace is used to create an API that gives G-Drive access to the ML algorithm. The system not only saves human work but also helps in increasing the quality of yield.
  • Performance analysis and improvement of a high-efficiency DCMLI based PMSM drive for electric vehicle using AVR microcontroller
    Rakesh Shriwastava, Nitin Dhote, Sunil Somnath Kadlag, Mohan P. Thakare, Deepak P. Kadam, Shridhar S. Khule
    International Journal of Vehicle Noise and Vibration, 2024
  • Preface
    Lecture Notes in Electrical Engineering, 2024
  • Towards Complexity, Area Reduction of Channelizer of Software Defined Radio
    Kirti S. Vaidya, C. G. Dethe, Sudhir Akojwar, Nitin Dhote
    Lecture Notes in Electrical Engineering, 2024
  • Power Control of Wind Energy Conversion System Using Super Capacitor
    Nitin K. Dhote, Swapna M. Choudhary, Rakesh Shrivastav, Kirti Vaidya, Deva Brinda
    Lecture Notes in Electrical Engineering, 2024
  • A multi-level neutral-point-clamped inverter driven PMSM high-speed electric drive
    Rakesh G. Shriwastava, Sunil S. Kadlag, Jagdish G. Chaudhari, Pratap R. Sonawane, Nitin Dhote
    International Journal of Electric and Hybrid Vehicles, 2024
  • Design of Spectral Absorbance-Based Electronic Reader for Chlorophyll Measurement
    Hema Kale, Yogita Nafde, Nitin Dhote, Swapna Choudhary
    Ssrg International Journal of Electrical and Electronics Engineering, 2023
  • IoT Based Smart Glasses with Facial Recognition for People with Visual Impairments
    Swapna Choudhary, Nitin Dhote, Ashwini A Deshpande, Ansh Sambhariya, Poorvi K Joshi
    Ssrg International Journal of Electrical and Electronics Engineering, 2023
  • The Light-On Project: Design and Construction of a Sun-Tracking System Using Image Processing
    H Stinia, K Kukliński, A Jaiswal, R Fadnavis, Sushmit Meshram, N Dhote, G Gadge, M Dudek, A Raźniak
    Iop Conference Series Earth and Environmental Science, 2021
  • IoT based Multi-point Pesticide Spraying Machine
    Swapna Choudhary, Kamlesh Kalbande, Nitin Dhote
    Proceedings of the 6th International Conference on Inventive Computation Technologies Icict 2021, 2021
  • Fuzzy system for transformer fault diagnosis and maintenance using DGA
    Journal of Electrical Engineering, 2014
  • Improvement in transformer diagnosis by DGA using fuzzy logic
    Nitin K. Dhote, J.B. Helonde
    Journal of Electrical Engineering and Technology, 2014
  • Fuzzy algorithm for power transformer diagnostics
    Nitin K. Dhote, Jagdish B. Helonde
    Advances in Fuzzy Systems, 2013
  • Diagnosis of power transformer faults based on five fuzzy ratio method
    Wseas Transactions on Power Systems, 2012
  • Development of an expert system for detecting incipient fault in transformer by dissolved gas analysis
    Iceis 2004 Proceedings of the Sixth International Conference on Enterprise Information Systems, 2004