Ashpana Dilawar Shiralkar

@aissmsioit.org

Associate Professor and Head of Electrical Engineering Department
AISSMS Institute of Information Technology Pune

Ashpana Dilawar Shiralkar


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

RESEARCH, TEACHING, or OTHER INTERESTS

Electrical and Electronic Engineering, Control and Systems Engineering, Renewable Energy, Sustainability and the Environment, Engineering
13

Scopus Publications

Scopus Publications

  • Message from Technical Program Chair, ICESCI-2026, Pune
    2026 International Conference on Emerging Smart Computing and Informatics Esci 2026, 2026
  • Extended state observer based output feedback control of 2 DoF electro hydraulic servo system
    Ashpana Shiralkar, Shailaja Kurode, Bhagyashri Tamhane
    Results in Control and Optimization, 2025
    Positioning a load in a two-dimensional subspace requires a two-degrees-of-freedom (2 DoF) position control system. The precise positioning of the load has been the driving motivation for electro-hydraulic actuation and its robust control. 2 DoF electro-hydraulic servo system (EHSS) is complex and nonlinear. Each of the 2 DoF is approximated by the second order model with uncertainty. A new sliding variable is proposed for precise finite-time positioning of a load. The extended state observer based controller is devised using higher-order sliding modes. Uncertainties and states are estimated to implement the controller in a finite time. The method is verified in both simulation and experiment. It is shown that the proposed method yield robust and precise positioning of load in two-dimensional subspace.
  • Enhancing Sugarcane Disease Classification Using Transfer Learning with Convolutional Neural Networks
    Meenakshi Thalor, Chinmay Nakwa, Sanjay Mate, Ashpana Shiralkar
    Ssrg International Journal of Electronics and Communication Engineering, 2025
    The economic implications of sugarcane diseases on local farmers in India are significant and multifaceted, affecting not only their immediate yields but also their overall financial stability and livelihoods. About 70 percent of India's rural households still primarily depend on agriculture for their livelihood. As a cash crop, sugarcane holds a very important place in India's agrarian economy. India is not only the largest consumer of sugar but also its second-largest producer. Identifying the diseases in their initial stages helps not only the farmer but also reduces the burden on the country in many aspects. This paper discusses DenseNet, VGG, and ConvNeXt for classifying diseases in sugarcane plants, along with the detailed experimentation conducted. Based on evaluation metrics, ConvNeXt outperforms with 96% accuracy compared to DenseNet and VGG architectures on sugarcane disease detection.
  • Machine Learning Based Decision Trees for Energy Meter Inspection in Power Sector
    Ashpana Shiralkar, Haripriya Kulkarni, Poonam Mane, Shashikant Bakre
    Ssrg International Journal of Electrical and Electronics Engineering, 2024
    This research paper presents an innovative approach to energy meter inspection within the power sector, leveraging the power of machine learning and decision tree analysis. The study seeks to enhance the accuracy and efficiency of inspections by employing a data-driven methodology. By utilizing decision trees, the model can effectively classify and identify meter anomalies, potential defects, and performance irregularities. The integration of machine learning enables the system to adapt and improve over time, ensuring precise and consistent inspections. The results indicate a significant improvement in inspection outcomes, reducing human error and enhancing the overall quality control process. This approach holds promise for more reliable and efficient energy meter inspections in the power sector, ultimately contributing to improved service quality and energy accountability. The novice Machine Learning approach method based on Decision trees and Random Forests is proposed based on a case study of one of the meter manufacturers in India.
  • A Drug Pill Recognition System for Visually Impaired People with Voice Assistant
    International Journal of Intelligent Systems and Applications in Engineering, 2024
  • Machine Learning Based Problem Solving Approach in Green Computing
    Shashikant Bakre, Ashpana Shiralkar, Sachin V. Shelar, Suchita Ingle
    2023 International Conference on Emerging Smart Computing and Informatics Esci 2023, 2023
    The issues related to conventional generation of electricity arethe matter of concern for power sector today. These include diminishing stock of coal over a period of time, unavailability of good quality coal, non-sustainable issues, ash handling problems etc. Green energy is the alternative to overcome these problems. The green energy is sustainable, renewable and economical. In India, the existing ratio of conventional to non-conventional generation as on 30th June 2022 is 72:28%. It is required to further improve this ratio to the tune of 60:40%. The performance of the green energy systems can be optimized by AI ML based green computing. Under the umbrella of AI, several technologies have been emerged. These technologies are machine learning, deep learning, data analytics, robotics, neural networks, expert systems, fuzzy logic systems, natural language processing, genetic algorithms etc. The green computing can be made more effective through research as regards how to use these technologies. In this paper, a novice techniques of AI ML based green computing have been proposed. Python programming language is used as a back end programming tool. The proposed methods are simple, cost effective and feasible.
  • Artificial Neural Network Based Electricity Theft Detection
    Shashikant Bakre, Ashpana Shiralkar, Sachin V. Shelar, Suchita Ingle
    2022 International Conference on Emerging Smart Computing and Informatics Esci 2022, 2022
    The theft of electricity is a matter of concern for the distribution utility today. The Aggregate Technical and Commercial (AT&C) loss of Maharashtra State Electricity Distribution Company is around 20.72% for the year 2020–21. The main cause of such a higher loss is pilferage or theft of electricity. As per statistics given by various distribution utilities, the theft incidences of three phase HT and LT consumers are under control. However, there is a rising trend in tampering of single phase meters. Various methods of theft detection of single phase meters are in existence, however, tampering of meter by inserting the resistive link in parallel with the meter cannot be detected using these conventional methods. In this paper, a novice technique of tamper detection using Artificial Neural Network is proposed. The proposed method is cost effective and feasible.
  • Artificial neural network based virtual energy meter
    Dinesh Pansare, Tejashree Mule, Nikita Markad, Ashpana Shiralkar, Shashikant Bakre
    2021 International Conference on Emerging Smart Computing and Informatics Esci 2021, 2021
    The concept of working of virtual meters has been emerged after evolution of IoT technology and cloud computing. In the meanwhile, the neural network models based on Python have also been emerged. In this paper, the concept of artificial neural network based virtual energy meter have been put forward. The logical AND gate based anomaly for virtual meter is presented. Secondly, using neural network based regression method, the novice method for power factor correction have been introduced. The computation of errors and adjustment of synaptic weights has been conducted using Python 3.0 version.
  • Arduino based PWM DC-DC boost converter for traction system
    Nilambari V Devarkar, , Mrs. Ashpana Shiralkar, and
    International Journal of Innovative Technology and Exploring Engineering, 2019
    Now a day’s energy conservation is the most important thing in the world wide. The area of traction also take this into the consideration, so they take a step forward to use regenerative energy which is generated through the regenerative braking in the train. This regenerated energy most of the time get wasted in form of heat. Or most of the time it fed back to overhead equipment. Using regenerative braking energy battery energy storage system is charging used in many countries like japan, New Zealand, UK. This paper presents the implementation of a dc dc boost converter which used this regenerated energy in the traction system and boost the voltage of battery energy storage system. This paper presents the improved dc-dc boost converter which can be implemented in future in the Indian railways system. Arduino based PMW dc dc converter used in traction system to charge the battery energy storage system.
  • Robust output feedback control of electro-hydraulic system
    Ashpana Shiralkar, Shailaja Kurode, Ruchira Gore, Bhagyashri Tamhane
    International Journal of Dynamics and Control, 2019
  • Incomplete state feedback control of Electro-Hydraulic Servo System using second order sliding modes
    Ruchira Gore, Ashpana Shiralkar, Shailaja Kurode
    Proceedings of IEEE International Workshop on Variable Structure Systems, 2016
  • Generalized super-twisting algorithm for control of electro-hydraulic servo system
    Ashpana Shiralkar, Shailaja Kurode
    IFAC Papersonline, 2016
  • Modeling of electro-hydraulic servo valve and robust position control using sliding mode technique
    1st International and 16th National Conference on Machines and Mechanisms Inacomm 2013, 2013