Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

An investigation of deep learning approaches for efficient assembly component identification

Published in Beni-Suef University Journal of Basic and Applied Sciences, 2024

This paper presents a deep learning-based system for automated identification of mechanical fasteners in manufacturing assembly processes. The study compares two object detection algorithms, Mask-RCNN and YOLO v5, for fastener detection using a custom dataset of over 6,000 images. YOLO v5 outperformed Mask-RCNN, achieving 99% mean average precision and demonstrating superior real-time performance, highlighting its potential to enhance automation and reliability in manufacturing operations.

Recommended citation: Ramesh, Kaki, Faisel Mushtaq, Sandip Deshmukh, Tathagata Ray, Chandu Parimi, Ali Basem, and Ammar Elsheikh. "An investigation of deep learning approaches for efficient assembly component identification." Beni-Suef University Journal of Basic and Applied Sciences 13, no. 1 (2024): 79.
Download Paper

Visualization experiment and machine learning modeling for falling-film systems

Published in Chemical Engineering Research and Design, 2023

This paper presents an experimental study on liquid film behavior in falling-film systems using high-speed imaging and machine learning techniques. It illustrates how parameters like Reynolds number and tube spacing affect flow characteristics such as jet diameter and film thickness, developing image analysis and machine learning models to quantify and predict these flow parameters for improved system design.

Recommended citation: Kandukuri, Prudviraj, Ramesh Kaki, Sandip Deshmukh, and Supradeepan Katiresan. "Visualization experiment and machine learning modeling for falling-film systems." Chemical Engineering Research and Design 199 (2023): 399-412.
Download Paper

Development of Machine Vision Approach for Mechanical Component Identification based on its Dimension and Pitch

Published in arXiv:2310.01995, 2023

This paper presents a vision-based system for automating mechanical assembly lines by identifying and classifying different types of bolts. The system uses a novel method to calculate bolt pitch and dimensions, achieving 98% accuracy in part identification with minimal hardware requirements and millisecond-level processing speeds, making it suitable for use with moving components on a conveyor.

Recommended citation: Jain, Toshit, Faisel Mushtaq, Kaki Ramesh, Sandip Deshmukh, Tathagata Ray, Chandu Parimi, Praveen Tandon, and Pramod Kumar Jha. "Development of Machine Vision Approach for Mechanical Component Identification based on its Dimension and Pitch." arXiv preprint arXiv:2310.01995 (2023).
Download Paper

Nuts&bolts: YOLO-v5 and image processing based component identification system

Published in Engineering Applications of Artificial Intelligence, 2022

This paper presents a deep learning and image processing approach for identifying mechanical fasteners in aerospace assembly lines. YOLO-v5 for component classification based on head and lateral shape is used and achieved 99.6% mean average precision. Also developed an image processing method to measure fastener dimensions, including thread pitch, with high accuracy (100% for standard sizes, max 0.05 mm error for pitch).

Recommended citation: Mushtaq, Faisel, Kaki Ramesh, Sandip Deshmukh, Tathagata Ray, Chandu Parimi, Praveen Tandon, and Pramod Kumar Jha. "Nuts&bolts: YOLO-v5 and image processing based component identification system." Engineering Applications of Artificial Intelligence 118 (2023): 105665.
Download Paper

Thermal conductivity prediction of titania-water nanofluid: A case study using different machine learning algorithms

Published in Case Studies in Thermal Engineering, 2021

This study compares five machine learning algorithms (ANN, GBR, SVR, DTR, and RFR) for predicting the thermal conductivity of TiO2-water nanofluids using a dataset of 228 data points. The gradient boosting regression (GBR) algorithm performed best, achieving 99% accuracy on both training and test sets, with the study also finding that nanoparticle shape significantly influences thermal conductivity predictions.

Recommended citation: Sharma, Palash, K. Ramesh, R. Parameshwaran, and Sandip S. Deshmukh. "Thermal conductivity prediction of titania-water nanofluid: A case study using different machine learning algorithms." Case Studies in Thermal Engineering 30 (2022): 101658.
Download Paper

Conference Papers

A Novel Approach to Generate Dataset for Object Detection in Assembly Lines

Published in Proc. International Conference on Mechanical, Automotive and Mechatronics Engineering (ICMAME 2023), 2023

This paper presents a deep learning approach to automate quality assurance in vehicle assembly, focusing on detecting cross marks on vehicle chassis. The researchers used the YOLOv5 model, adapting its architecture and parameters for this specific task. Achieved high accuracy, with a mean average precision (mAP) of 98% or higher, demonstrating the potential of deep learning to improve precision and reduce errors in vehicle assembly quality control.

Recommended citation: Ramesh kaki, samarth Soni, Sandip Deshmukh, Tathagata Ray, Chandu Parimi, A Novel Approach to Generate Dataset for Object Detection in Assembly Lines, Proc. International Conference on Mechanical, Automotive and Mechatronics Engineering (ICMAME 2023).
Download Paper

Identification of SMAW Surface Weld Defects Using Machine Learning

Published in Recent Advances in Materials Processing and Characterization, 2022

This paper presents a machine learning approach for identifying surface defects in shielded metal arc welding (SMAW) using high-resolution images. Applied various image processing techniques to extract geometrical features of welds, then built CNN and ResNet50 models to classify acceptable beads and surface defects, achieving over 98% accuracy for both models.

Recommended citation: Ramesh, K., E. V. Ramana, L. Srikanth, C. Sri Harsha, and N. Kiran Kumar. "Identification of SMAW Surface Weld Defects Using Machine Learning." In Recent Advances in Materials Processing and Characterization: Select Proceedings of ICMPC 2021, pp. 339-350. Singapore: Springer Nature Singapore, 2022.
Download Paper