Vidyasagar Sugavanam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Vidyasagar Sugavanam has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Krishnasamy Vijayakumar
Department of Electronics and Communication Engineering, Indian Institute of Information Technology, Design and Manufacturing, Kancheepuram, Chennai, India
6 shared publications - Dasarathan Sattianadan
Department of Electrical and Electronics Engineering, SRM Institute of Science and Technology, Kattankulathur 603203, Tamil Nadu, India
4 shared publications - Ramasamy Palanisamy
SRM Institute of Science and Technology
3 shared publications D. Sattianadan
SRM Institute of Science and Technology, India
2 shared publications- Kalyanasundaram Vakesan
SRM Institute of Science and Technology, India
2 shared publications - Shanmugapriya Veerapandiyan
Department of Electrical and Electronics Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu, India
2 shared publications
Latest Publications
- 28 March 2026
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (16)
Development of a High-Performance Regenerative Shock Absorber Utilizing Helical Gears for Efficient Energy Harvesting and Range Extension in Electric Vehicles
Electric vehicles (EVs) rely on efficient energy management to extend driving range, and regenerative shock absorbers using helical gears can capture kinetic energy from suspension motion. Key challenges include mechanical complexity, vibration damping and maximizing energy conversion without compromising ride comfort. This paper proposes a combined approach for an efficient regenerative absorber related to a twin helical-gear for range-extended EVs. The proposed absorber converts suspension vibrations from road roughness into electricity using a suspension input module, helical gears, one-way clutches and a generator module. The proposed approach combines the techniques of the Electric Eel Foraging Optimization (EEFO) Method and Generative Pre-Trained Physics-Informed Neural Networks (GPT-PINNs). Hence, it is called the EEFO-GPT-PINNs technique. The EEFO is utilized to optimize the motor driving system’s power consumption, while the GPT-PINNs method is utilized to forecast the EV Range based on current driving conditions. To increase the efficiency of energy transfer, the adaptive EEFO-GPT-PINNs optimize the one-way clutches and helical gears. The objective of this work is to develop the efficiency and power of the system. The proposed strategy is implemented and analyzed using MATLAB and its performance is compared with existing methods, including Proximal Policy Optimization (PPO), Multi-Objective Optimization (MOO) and Genetic Algorithm (GA) techniques. The proposed approach achieves significant improvements, yielding 21% higher energy harvesting at a damping ratio of 0.1[ ]m/s, 46% mechanical efficiency at 6[ ]Hz and 94% recoverable power effectiveness at 3[ ]Hz, thereby outperforming existing methods and validating its potential for enhanced power and efficiency optimization.
- 28 March 2026
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 35 (16)
Development of a High-Performance Regenerative Shock Absorber Utilizing Helical Gears for Efficient Energy Harvesting and Range Extension in Electric Vehicles
Electric vehicles (EVs) rely on efficient energy management to extend driving range, and regenerative shock absorbers using helical gears can capture kinetic energy from suspension motion. Key challenges include mechanical complexity, vibration damping and maximizing energy conversion without compromising ride comfort. This paper proposes a combined approach for an efficient regenerative absorber related to a twin helical-gear for range-extended EVs. The proposed absorber converts suspension vibrations from road roughness into electricity using a suspension input module, helical gears, one-way clutches and a generator module. The proposed approach combines the techniques of the Electric Eel Foraging Optimization (EEFO) Method and Generative Pre-Trained Physics-Informed Neural Networks (GPT-PINNs). Hence, it is called the EEFO-GPT-PINNs technique. The EEFO is utilized to optimize the motor driving system’s power consumption, while the GPT-PINNs method is utilized to forecast the EV Range based on current driving conditions. To increase the efficiency of energy transfer, the adaptive EEFO-GPT-PINNs optimize the one-way clutches and helical gears. The objective of this work is to develop the efficiency and power of the system. The proposed strategy is implemented and analyzed using MATLAB and its performance is compared with existing methods, including Proximal Policy Optimization (PPO), Multi-Objective Optimization (MOO) and Genetic Algorithm (GA) techniques. The proposed approach achieves significant improvements, yielding 21% higher energy harvesting at a damping ratio of 0.1[ ]m/s, 46% mechanical efficiency at 6[ ]Hz and 94% recoverable power effectiveness at 3[ ]Hz, thereby outperforming existing methods and validating its potential for enhanced power and efficiency optimization.
- 27 March 2026
- Published by IGI Global Scientific Publishing
- p. 59-84
Artificial Intelligence in Sustainable Supply Chain Management
Artificial Intelligence (AI) is transforming sustainable supply chain management by enhancing operational efficiency, strengthening resilience, and reducing environmental impact. This chapter explores the integration of AI techniques including machine learning, deep learning, optimization models, and digital twins across key supply chain functions such as forecasting, manufacturing, logistics, procurement, and circular resource management. AI-driven tools improve demand prediction, energy optimization, carbon tracking, waste reduction, and risk mitigation while enabling real-time visibility and data-driven decision-making. The chapter also discusses challenges related to data quality, computational demands, cybersecurity, bias, and regulatory constraints. Future opportunities, such as autonomous supply chains, green AI, and integration with IoT and blockchain, highlight AI's potential to support long-term sustainability goals.
- 27 March 2026
- Published by IGI Global Scientific Publishing
- p. 59-84
Artificial Intelligence in Sustainable Supply Chain Management
Artificial Intelligence (AI) is transforming sustainable supply chain management by enhancing operational efficiency, strengthening resilience, and reducing environmental impact. This chapter explores the integration of AI techniques including machine learning, deep learning, optimization models, and digital twins across key supply chain functions such as forecasting, manufacturing, logistics, procurement, and circular resource management. AI-driven tools improve demand prediction, energy optimization, carbon tracking, waste reduction, and risk mitigation while enabling real-time visibility and data-driven decision-making. The chapter also discusses challenges related to data quality, computational demands, cybersecurity, bias, and regulatory constraints. Future opportunities, such as autonomous supply chains, green AI, and integration with IoT and blockchain, highlight AI's potential to support long-term sustainability goals.
- Open Access
- 5 April 2025
- Published by Science Research Society in Journal of Information Systems Engineering and Management
- Vol. 10 (32s) , 821-828
Analyzing the Environmental Burden of Electric Vehicle Batteries: A Life Cycle Assessment Synthesis
Introduction: The rapid growth of the EV market and the associated surge in battery demand raise environmental concerns regarding battery production and disposal. While EVs have zero tailpipe emissions, battery production contributes significantly to their overall environmental burden. Life Cycle Assessment (LCA) is a crucial tool for evaluating this impact, but inconsistencies in methodologies across different LCA studies hinder effective comparison and progress towards cleaner battery technologies. Objectives: The research aims to analyze numerous existing LCA studies on electric vehicle batteries using a standardized approach based on ISO 14040 guidelines. The goal is to ensure consistent comparisons and identify areas for environmental improvement throughout the battery life cycle. Methods: This review examines 20 relevant LCA studies on single battery models published between 2018 and 2023. It critically appraises these studies based on the ISO 14040 framework, focusing on the four key stages of LCA: defining objectives and scope, conducting inventory analysis, performing impact assessment, and interpreting the results. Results: The review found significant variability in methodologies, system boundaries (cradle-to-gate vs. cradle-to-grave), functional units, data sources (primary vs. secondary), and impact assessment methods used in the analyzed LCA studies. The production phase and the product use phase were identified as having the most significant environmental impacts. Global warming was the most frequently studied impact category. Conclusions: The inconsistency in LCA studies on EV batteries necessitates a more standardized approach. The author recommends using a cradle-to-grave system boundary, a consistent functional unit (like "kilometer traveled" or "kilowatt-hour of energy delivered over the battery's lifetime"), and a core set of nine relevant impact categories. Transparency in methodology, assumptions, and data quality is crucial for ensuring reliable and comparable results, ultimately informing efforts to improve the environmental performance of EV batteries.
- 5 April 2025
- Published by Science Research Society in Journal of Information Systems Engineering and Management
- Vol. 10 (32s) , 821-828
Open AccessAnalyzing the Environmental Burden of Electric Vehicle Batteries: A Life Cycle Assessment Synthesis
Introduction: The rapid growth of the EV market and the associated surge in battery demand raise environmental concerns regarding battery production and disposal. While EVs have zero tailpipe emissions, battery production contributes significantly to their overall environmental burden. Life Cycle Assessment (LCA) is a crucial tool for evaluating this impact, but inconsistencies in methodologies across different LCA studies hinder effective comparison and progress towards cleaner battery technologies. Objectives: The research aims to analyze numerous existing LCA studies on electric vehicle batteries using a standardized approach based on ISO 14040 guidelines. The goal is to ensure consistent comparisons and identify areas for environmental improvement throughout the battery life cycle. Methods: This review examines 20 relevant LCA studies on single battery models published between 2018 and 2023. It critically appraises these studies based on the ISO 14040 framework, focusing on the four key stages of LCA: defining objectives and scope, conducting inventory analysis, performing impact assessment, and interpreting the results. Results: The review found significant variability in methodologies, system boundaries (cradle-to-gate vs. cradle-to-grave), functional units, data sources (primary vs. secondary), and impact assessment methods used in the analyzed LCA studies. The production phase and the product use phase were identified as having the most significant environmental impacts. Global warming was the most frequently studied impact category. Conclusions: The inconsistency in LCA studies on EV batteries necessitates a more standardized approach. The author recommends using a cradle-to-grave system boundary, a consistent functional unit (like "kilometer traveled" or "kilowatt-hour of energy delivered over the battery's lifetime"), and a core set of nine relevant impact categories. Transparency in methodology, assumptions, and data quality is crucial for ensuring reliable and comparable results, ultimately informing efforts to improve the environmental performance of EV batteries.
- Open Access
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 36 (3) , 1976-1984
Space vector pulse width modulation realization for three-phase voltage source inverter
This paper presents the implementation of space vector pulse width modulation (SVPWM) for a three-phase voltage source inverter (VSI). SVPWM is a technique used to control the output voltage of VSIs with improved efficiency and precision. The abstract outlines the key steps involved in implementing SVPWM, including reference signal clarification, sector identification, determination of voltage vectors, and switching state calculation. This proposed system provides improved output voltage of the inverter, minimized voltage stress across the switches and reduced total harmonic distortion and electromagnetic interference. The proposed implementation aims to enhance the performance of three-phase VSIs in various applications, such as motor drives, renewable energy systems, and power converters. The simulation results of proposed system are verified using MATLAB Simulink.
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 36 (3) , 1976-1984
Open AccessSpace vector pulse width modulation realization for three-phase voltage source inverter
This paper presents the implementation of space vector pulse width modulation (SVPWM) for a three-phase voltage source inverter (VSI). SVPWM is a technique used to control the output voltage of VSIs with improved efficiency and precision. The abstract outlines the key steps involved in implementing SVPWM, including reference signal clarification, sector identification, determination of voltage vectors, and switching state calculation. This proposed system provides improved output voltage of the inverter, minimized voltage stress across the switches and reduced total harmonic distortion and electromagnetic interference. The proposed implementation aims to enhance the performance of three-phase VSIs in various applications, such as motor drives, renewable energy systems, and power converters. The simulation results of proposed system are verified using MATLAB Simulink.
- 6 March 2023
- Published by Taylor & Francis in Electric Power Components and Systems
- Vol. 51 (8) , 785-808
On-Line Fault Identification, Location, and Seamless Service Restoration using Transfer Learning-Based Convolution Neural Network for Low-Voltage DC Microgrid
DC microgrid over the last decade has gained a global paradigm in the power system field. Through the effective integration of distributed energy resources, significant researchers have improved its advantages over conventional power systems. The new state-of-the-art infrastructure despite its numerous advantages possess challenges in implementing an appropriate protection system. Impact of selecting a definite threshold for voltage and current compromises with the accuracy and speed of detection in conventional fault detection methods. Although many machine learning methods are successful in fault detection and classification for DC microgrid they still suffer from overfitting problems and exhaustively time-consuming. This article intends to provide an Online fault protection method for a LVDC microgrid system based on a transfer learning-based convolution neural network (TCNN). With the help of transient voltages and currents at different buses, image data for faults at different buses serves as input to the convolution neural network layer. First, the pre-trained Alex-Net CNN initializes the weights and biases for the targeted offline CNN’s. Secondly, the transferred layers from the offline CNN’s, initializes the online convolution neural network for real-time fault detection and classification. This work aims to accurately identify and locate the faults without complex dataset and multiple thresholds while improving accuracy of fault detection and classification. To ensure reliability of the system the recognized faulty bus reconnects to the healthy bus via sectionalizing circuit breakers through the detected signals. The proposed TCNN framework has an accuracy of 99.78%. The proposed method results when compared with state-of-the-art machine learning techniques such as SVM, LSTM, RNN, multilayer perceptron, and wavelet-based ANN showed better results in terms of accuracy and has significantly reduced data abundance.
- 6 March 2023
- Published by Taylor & Francis in Electric Power Components and Systems
- Vol. 51 (8) , 785-808
On-Line Fault Identification, Location, and Seamless Service Restoration using Transfer Learning-Based Convolution Neural Network for Low-Voltage DC Microgrid
DC microgrid over the last decade has gained a global paradigm in the power system field. Through the effective integration of distributed energy resources, significant researchers have improved its advantages over conventional power systems. The new state-of-the-art infrastructure despite its numerous advantages possess challenges in implementing an appropriate protection system. Impact of selecting a definite threshold for voltage and current compromises with the accuracy and speed of detection in conventional fault detection methods. Although many machine learning methods are successful in fault detection and classification for DC microgrid they still suffer from overfitting problems and exhaustively time-consuming. This article intends to provide an Online fault protection method for a LVDC microgrid system based on a transfer learning-based convolution neural network (TCNN). With the help of transient voltages and currents at different buses, image data for faults at different buses serves as input to the convolution neural network layer. First, the pre-trained Alex-Net CNN initializes the weights and biases for the targeted offline CNN’s. Secondly, the transferred layers from the offline CNN’s, initializes the online convolution neural network for real-time fault detection and classification. This work aims to accurately identify and locate the faults without complex dataset and multiple thresholds while improving accuracy of fault detection and classification. To ensure reliability of the system the recognized faulty bus reconnects to the healthy bus via sectionalizing circuit breakers through the detected signals. The proposed TCNN framework has an accuracy of 99.78%. The proposed method results when compared with state-of-the-art machine learning techniques such as SVM, LSTM, RNN, multilayer perceptron, and wavelet-based ANN showed better results in terms of accuracy and has significantly reduced data abundance.
- Open Access
- 1 January 2023
- Published by International Journal of Renewable Energy Research in International Journal of Renewable Energy Research
- Vol. 13 (V32i3) , 1259-1276
SMART ENERGY MANAGEMENT FOR A HYBRID DC MICROGRID ELECTRIC VEHICLE CHARGING STATION
Electric Vehicles (EVs) are increasing in popularity due to their environment-friendly, lower-cost operation and technology elevation. With these advancements and new technologies come more significant challenges and opportunities. The increasing power demand and emerging EV usage reflect enhanced renewable energies such as PV power along with smart storage devices. Nevertheless, an EV charging station for a residential building or a parking lot powered through grid-connected local PV generation has specific uncertainty issues and energy management problems. Some of the main areas to investigate are selecting Energy Storage devices with adequate capacity, grid-PV integration, and energy management for maintaining constant EV charging station requirements based on the EV’s State of Charge (SOC). This study proposes an intelligent, coordinated energy management strategy between the PV power station, the grid, the ESS, and the EV charging station. Here, a smart Energy Management system (EMS) based on Convolution Neural Network – Long Short Term Memory (CNN-LSTM) is proposed for the real-time changes in solar irradiance and State of Charge (SOC) of the ESS to manage grid power and local PV to maintain EV charging station requirements. Moreover, the proposed method prioritizes the usage of Renewable PV sources for the EV charging station, making this eco-friendly and sustainable. Simulation results illustrate the effective integration of the proposed EMS.
- 1 January 2023
- Published by International Journal of Renewable Energy Research in International Journal of Renewable Energy Research
- Vol. 13 (V32i3) , 1259-1276
Open AccessSMART ENERGY MANAGEMENT FOR A HYBRID DC MICROGRID ELECTRIC VEHICLE CHARGING STATION
Electric Vehicles (EVs) are increasing in popularity due to their environment-friendly, lower-cost operation and technology elevation. With these advancements and new technologies come more significant challenges and opportunities. The increasing power demand and emerging EV usage reflect enhanced renewable energies such as PV power along with smart storage devices. Nevertheless, an EV charging station for a residential building or a parking lot powered through grid-connected local PV generation has specific uncertainty issues and energy management problems. Some of the main areas to investigate are selecting Energy Storage devices with adequate capacity, grid-PV integration, and energy management for maintaining constant EV charging station requirements based on the EV’s State of Charge (SOC). This study proposes an intelligent, coordinated energy management strategy between the PV power station, the grid, the ESS, and the EV charging station. Here, a smart Energy Management system (EMS) based on Convolution Neural Network – Long Short Term Memory (CNN-LSTM) is proposed for the real-time changes in solar irradiance and State of Charge (SOC) of the ESS to manage grid power and local PV to maintain EV charging station requirements. Moreover, the proposed method prioritizes the usage of Renewable PV sources for the EV charging station, making this eco-friendly and sustainable. Simulation results illustrate the effective integration of the proposed EMS.
- Open Access
- 1 December 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 13 (4) , 2269-2276
A novel SVPWM for 3-phase to 5-phase conversion using matrix converter
A novel matrix converter has been developed for 3-phase to 5-phase conversion using a novel space vector pulse width modulation. The matrix converter organized to generate 5-phase AC output voltage from 3-phase input voltage with help of SVPWM method; bidirectional power switches placed in matrix converter controlled by appropriate switching pulse. Space vector pulse width modulation (SVPWM) provides better utilization of applied input voltage, improved output voltage, reduced total harmonic distortion. The bidirectional switch used by the matrix converter decreases stress on the power switch and the influence of harmonic fluctuation in AC output voltage. When compared to traditional approaches, the suggested system offers improved output voltage and current control. Using MATLAB/Simulink and FPGA-cyclone controller, respectively, modelling and experimental results have been given to validate the proposed methodology.
- 1 December 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 13 (4) , 2269-2276
Open AccessA novel SVPWM for 3-phase to 5-phase conversion using matrix converter
A novel matrix converter has been developed for 3-phase to 5-phase conversion using a novel space vector pulse width modulation. The matrix converter organized to generate 5-phase AC output voltage from 3-phase input voltage with help of SVPWM method; bidirectional power switches placed in matrix converter controlled by appropriate switching pulse. Space vector pulse width modulation (SVPWM) provides better utilization of applied input voltage, improved output voltage, reduced total harmonic distortion. The bidirectional switch used by the matrix converter decreases stress on the power switch and the influence of harmonic fluctuation in AC output voltage. When compared to traditional approaches, the suggested system offers improved output voltage and current control. Using MATLAB/Simulink and FPGA-cyclone controller, respectively, modelling and experimental results have been given to validate the proposed methodology.
- 9 September 2020
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 15 (6) , 2639-2649
A SVPWM Control Strategy for Capacitor Voltage Balancing of Flying Capacitor Based 4-Level NPC Inverter
- 9 September 2020
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 15 (6) , 2639-2649
A SVPWM Control Strategy for Capacitor Voltage Balancing of Flying Capacitor Based 4-Level NPC Inverter
- Open Access
- 17 November 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (42)
Enhancement of Distribution System Loadability DG under Reconfigured Environment
Objectives: In this paper a comprehensive analysis of DG is done under initial configuration (base case) as well as with the feeder reconfigured environment in order to minimize the losses and to enhance voltage stability index. Methods/Analysis: In today’s trend delivery of power to customers have become a major issue in the field of power systems, one as such solution to this issue is usage of small units named as Distributed Generators (DG) entered the area of distribution systems. Findings: With the involvement of DG’s, a given system can achieve an improvement in terms of reliability, stability and reduction of losses. It just not only by using DG alone will solve the issue, but also mainly we have to focus on its location, size and the type which has to be used. Application /Improvement: For this analysis a standard IEEE 33-bus and 69-bus test distribution system is taken under nominal load consideration and the results are tabulated.
- 17 November 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (42)
Open AccessEnhancement of Distribution System Loadability DG under Reconfigured Environment
Objectives: In this paper a comprehensive analysis of DG is done under initial configuration (base case) as well as with the feeder reconfigured environment in order to minimize the losses and to enhance voltage stability index. Methods/Analysis: In today’s trend delivery of power to customers have become a major issue in the field of power systems, one as such solution to this issue is usage of small units named as Distributed Generators (DG) entered the area of distribution systems. Findings: With the involvement of DG’s, a given system can achieve an improvement in terms of reliability, stability and reduction of losses. It just not only by using DG alone will solve the issue, but also mainly we have to focus on its location, size and the type which has to be used. Application /Improvement: For this analysis a standard IEEE 33-bus and 69-bus test distribution system is taken under nominal load consideration and the results are tabulated.