16 September 2022 in Journal of Applied Physics
This paper explores the feasibility of machine learning algorithms on nonlinear ultrasonics for classification of the austenitic stainless-steel material subjected to different annealing conditions. The material that is isothermally annealed at 1323 K for different soaking times showed a marginal variation in its nonlinearity parameter at larger mean grain sizes. The grain growth during annealing followed the Arrhenius type equation fairly well, which has been verified using a genetic algorithm approach. The machine learning algorithms are trained using features such as the ratio of the harmonic amplitudes, root-mean-square value, and the phase difference between the fundamental and second harmonic components derived from the nonlinear ultrasonic response. Upon evaluating the performance of decision tree and ensemble learning algorithms in the classification of annealed materials, it was observed that the LPBoost classifier has the highest accuracy of 97%. According to the results, it is concluded that a machine learning strategy based on a minimal number of features can effectively classify specimens that are otherwise indistinguishable in their nonlinear response. This research takes a step forward to the automation of non-destructive testing toward Industrial Revolution 4.0. The results also pointed out the necessity of parameter fusion in non-destructive decision making.
20 March 2025 in International Journal of Mechanical Engineering Education
PLPavan Kalyan Lingampally
At present, society needs engineers capable of meeting societal needs with minimal cost and effective utilization of resources. This requires engineers to be well-equipped with both theoretical and practical knowledge to understand, solve, and apply engineering principles. Traditional engineering education has primarily focused on imparting theoretical knowledge, often neglecting the practical approach. This study explores the role of Project-Based Learning in enhancing teaching and learning in a first-year core course in Mechatronics Engineering. The primary objective was to enable students to integrate theoretical concepts with practical applications, addressing real-world challenges effectively. Students were tasked with identifying gaps, formulating project ideas, designing solutions, selecting components, and iterating their designs based on real-world constraints. Findings indicate that this method significantly improved students’ problem-solving skills, creativity, and teamwork. They also demonstrated a better understanding of engineering concepts and completed cost-effective projects, most within $10, by using available resources. Therefore, this practical approach enhances students’ problem-solving abilities, creativity, and teamwork skills, enabling them to apply their knowledge in addressing societal challenges they will face in their professional careers.
22 March 2022 in Journal of Applied Physics
Sorting of materials at different stages of manufacturing processes is very important to ensure the final product quality. In this paper, the machine learning algorithms are used on the magnetic Barkhausen emission (MBE) signals for the classification of martensitic stainless-steel specimens, which are subjected to different heat treatments. The variation in MBE parameters, such as root mean square, peak height, peak position, and full width at half maximum, was found to be marginal for normalized and quenching and partitioned specimens even though their x-ray diffraction analysis showed distinct microstructural conditions. The conventional MBE parameters are used to train the machine learning models. The performance of decision tree and ensemble learning techniques, such as Bagging, Random Subspace, AdaBoost, RUSBoost, Total Boost, and LP Boost classifiers, is compared and found that the AdaBoost classifier provides the maximum accuracy of 98% in the classification of complex materials. The results showed that the machine learning approach using a limited number of features is sufficiently sensitive toward the classification of specimens that are otherwise indistinguishable in their conventional MBE response.
1 December 2024 in IAES International Journal of Robotics and Automation (IJRA)
This research presents a comprehensive design and analysis of a knee rehabilitation platform aimed at aiding individuals with knee dysfunction. Dysfunction in the knee joint can lead to an imbalance in gait and posture during activities of daily living (ADLs) such as standing, walking, and running. This study focuses on developing a 2-degree-of-freedom (2-DoF) knee rehabilitation device capable of mimicking linear and angular movements. A slider mechanism-based knee rehabilitation device is developed and simulated alongside various other mechanisms. The proposed mechanism achieves 32.5° of flexion for a linear movement of 0.45 m within 6 seconds, outperforming other mechanisms. To validate simulation results, a 3D-printed model is fabricated, and experimental studies are conducted under no-load conditions, showing close alignment with simulation outcomes with a deviation of ±5%. The device’s key features include portability, compliance, compactness, and enhanced stiffness. Future research will involve conducting pilot studies to further evaluate the practical efficacy and potential enhancements of the proposed knee rehabilitation platform.
1 January 2023 in AIP Conference Proceedings
Lower limb motor or knee joints are one the most vulnerable joints among the human joints. These knee joints play a major role in supporting the entire weight o
4 July 2023 in Research in Nondestructive Evaluation