Pravin Hujare
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pravin Hujare has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Deepak Hujare
2 shared publicationsUmesh Chavan
2 shared publications- Anand K. Bewoor
Cummins College of Engineering for Women, Pune, India
1 shared publication Ashok R Mache
Department of Mechanical Engineering, Vishwakarma Institute of Information Technology, Savitribai Phule Pune University, Pune, India
1 shared publicationAsitang Lahurikar
1 shared publicationBhagyesh Pingle
1 shared publication
Latest Publications
- 27 February 2026
- Published by Springer Nature in Journal of Vibration Engineering & Technologies
- Vol. 14 (3)
A Comprehensive Investigation on the Dynamic Performance of Anti-Vibration Mounts
- 27 February 2026
- Published by Springer Nature in Journal of Vibration Engineering & Technologies
- Vol. 14 (3)
A Comprehensive Investigation on the Dynamic Performance of Anti-Vibration Mounts
- Open Access
- 26 September 2025
- Published by Springer Nature in Journal of Engineering and Applied Science
- Vol. 72 (1) , 1-28
Analysis of compressor performance using data-driven machine learning techniques
The verification of mathematical models for multistage reciprocating compressors is crucial for ensuring their accuracy and reliability. In this study, we used different machine learning (ML) models to verify the results of MATLAB-based models of single-stage reciprocating compressors, multistage reciprocating compressors without intercoolers, and multistage reciprocating compressors with intercoolers to simulate the real-world operating conditions of a reciprocating compressor. The verification focuses on key performance indicators, such as the pressure–volume (PV) graph, outlet temperature graph, volumetric efficiency, and pressure ratio graph. The MATLAB model computes thermodynamic parameters, such as the power required, outlet pressure, and outlet temperature for various operating conditions. The MATLAB model produced the following results for single-stage compressor: the outlet pressure increased by 1.6 times the inlet pressure of the compressor, the volume reduced by 20% of the volume at the inlet of the single-stage compressor, and the outlet temperature increased by 30% of the inlet temperature. In the case of a multistage compressor without an intercooler, the outlet pressure increased by about 3.3–3.6 times the inlet pressure of the compressor; the volume reduced by 60% of the volume at the inlet, and the outlet temperature increased by 35% in comparison to the inlet temperature of the multistage compressor without an intercooler. Subsequently, in the case of a multistage compressor with an intercooler at the first stage of compression, the pressure increased by three times the inlet pressure; at the second stage of compression, the pressure increased by six times the inlet pressure of the compressor, the volume was reduced by approximately 80%, and the intercooler maintained the increase in outlet temperature by 30%, limiting it and preventing excessive expansion of air in the compressor and increasing the efficiency of the compressor by 12% in comparison to the multistage compressor without an intercooler. In addition, the results generated by all the machine learning models used in the study were in correlation with the results generated by the MATLAB model for all three compressors, with an accuracy of approximately 90% or more for almost all the models implemented for prediction. By comparing the predicted outputs from the ML model with the MATLAB-generated results, the accuracy and consistency of the simulation were assessed. This study aims to bridge the gap between traditional mathematical modeling and modern data-driven validation techniques to ensure robustness in compressor performance predictions.
- 26 September 2025
- Published by Springer Nature in Journal of Engineering and Applied Science
- Vol. 72 (1) , 1-28
Open AccessAnalysis of compressor performance using data-driven machine learning techniques
The verification of mathematical models for multistage reciprocating compressors is crucial for ensuring their accuracy and reliability. In this study, we used different machine learning (ML) models to verify the results of MATLAB-based models of single-stage reciprocating compressors, multistage reciprocating compressors without intercoolers, and multistage reciprocating compressors with intercoolers to simulate the real-world operating conditions of a reciprocating compressor. The verification focuses on key performance indicators, such as the pressure–volume (PV) graph, outlet temperature graph, volumetric efficiency, and pressure ratio graph. The MATLAB model computes thermodynamic parameters, such as the power required, outlet pressure, and outlet temperature for various operating conditions. The MATLAB model produced the following results for single-stage compressor: the outlet pressure increased by 1.6 times the inlet pressure of the compressor, the volume reduced by 20% of the volume at the inlet of the single-stage compressor, and the outlet temperature increased by 30% of the inlet temperature. In the case of a multistage compressor without an intercooler, the outlet pressure increased by about 3.3–3.6 times the inlet pressure of the compressor; the volume reduced by 60% of the volume at the inlet, and the outlet temperature increased by 35% in comparison to the inlet temperature of the multistage compressor without an intercooler. Subsequently, in the case of a multistage compressor with an intercooler at the first stage of compression, the pressure increased by three times the inlet pressure; at the second stage of compression, the pressure increased by six times the inlet pressure of the compressor, the volume was reduced by approximately 80%, and the intercooler maintained the increase in outlet temperature by 30%, limiting it and preventing excessive expansion of air in the compressor and increasing the efficiency of the compressor by 12% in comparison to the multistage compressor without an intercooler. In addition, the results generated by all the machine learning models used in the study were in correlation with the results generated by the MATLAB model for all three compressors, with an accuracy of approximately 90% or more for almost all the models implemented for prediction. By comparing the predicted outputs from the ML model with the MATLAB-generated results, the accuracy and consistency of the simulation were assessed. This study aims to bridge the gap between traditional mathematical modeling and modern data-driven validation techniques to ensure robustness in compressor performance predictions.
- Open Access
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (2) , 1345-1354
Deep learning-based classifier for geometric dimensioning and tolerancing symbols
This research investigates the recognition of geometric dimensioning and tolerancing (GD&T) symbols using a deep learning model for object detection. GD&T, playing a pivotal role in engineering and manufacturing, provides essential specifications for product design and production. Manual processes for GD&T are often time-consuming and error prone. The study demonstrates outstanding accuracy in automating GD&T symbol recognition in engineering applications using YOLOv8. A carefully curated dataset, encompassing a wide range of GD&T symbols, was employed for training and evaluating the model. The YOLOv8 architecture, renowned for its robust performance, was meticulously fine-tuned to cater to the specific requirements of GD&T symbol detection. This research not only addresses the challenges in manual GD&T processes but also showcases practical implications for improved quality control and streamlined engineering workflows. By automating GD&T symbol recognition, this study contributes to the efficiency and precision crucial in the engineering and manufacturing domains.
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (2) , 1345-1354
Open AccessDeep learning-based classifier for geometric dimensioning and tolerancing symbols
This research investigates the recognition of geometric dimensioning and tolerancing (GD&T) symbols using a deep learning model for object detection. GD&T, playing a pivotal role in engineering and manufacturing, provides essential specifications for product design and production. Manual processes for GD&T are often time-consuming and error prone. The study demonstrates outstanding accuracy in automating GD&T symbol recognition in engineering applications using YOLOv8. A carefully curated dataset, encompassing a wide range of GD&T symbols, was employed for training and evaluating the model. The YOLOv8 architecture, renowned for its robust performance, was meticulously fine-tuned to cater to the specific requirements of GD&T symbol detection. This research not only addresses the challenges in manual GD&T processes but also showcases practical implications for improved quality control and streamlined engineering workflows. By automating GD&T symbol recognition, this study contributes to the efficiency and precision crucial in the engineering and manufacturing domains.
- 26 July 2021
- Published by SAGE Publications in Noise & Vibration Worldwide
- Vol. 52 (9) , 285-292
Analysis for effect of pores on acoustic performance of reactive muffler
The major source of noise pollution was an internal combustion engine. Henceforth, the design of the engine exhaust system was a tough challenge for automotive industries. The mufflers have been used to moderate the exhaust noise from the engine to the neighboring atmosphere. So in domestic as well as the industrial application, it is required to reduce noise levels to prevent human hazards. The performance of muffler is measured in terms of transmission loss. The transmission loss of reactive muffler is depending on its geometry. This article describes the effects of pores at the inlet pipe and outlet pipe of the reactive muffler on its performance capacity at a target frequency. It is found that the muffler performance is dependent on the number and position of pores. The single chamber and double chamber reactive mufflers are used for the study. The numerical analysis is performed by COMSOL Multiphysics software. The numerical analysis result of the different models of the muffler is compared with experimental analysis. The purpose of the study is to investigate the effect of pores in inlet and outlet pipe to maximize the TL at the target frequency of reactive muffler.
- 26 July 2021
- Published by SAGE Publications in Noise & Vibration Worldwide
- Vol. 52 (9) , 285-292
Analysis for effect of pores on acoustic performance of reactive muffler
The major source of noise pollution was an internal combustion engine. Henceforth, the design of the engine exhaust system was a tough challenge for automotive industries. The mufflers have been used to moderate the exhaust noise from the engine to the neighboring atmosphere. So in domestic as well as the industrial application, it is required to reduce noise levels to prevent human hazards. The performance of muffler is measured in terms of transmission loss. The transmission loss of reactive muffler is depending on its geometry. This article describes the effects of pores at the inlet pipe and outlet pipe of the reactive muffler on its performance capacity at a target frequency. It is found that the muffler performance is dependent on the number and position of pores. The single chamber and double chamber reactive mufflers are used for the study. The numerical analysis is performed by COMSOL Multiphysics software. The numerical analysis result of the different models of the muffler is compared with experimental analysis. The purpose of the study is to investigate the effect of pores in inlet and outlet pipe to maximize the TL at the target frequency of reactive muffler.