Sidhaant Rishi

Worked at the intersection of structural dynamics, simulation, and predictive maintenance for over two years. Performed modal analysis in Abaqus to support elastic-MBS models and translated a MATLAB-based elastomeric coupling model into a vectorized Python tool for torque prediction. Redesigned clutch adapter CADs for multi-configuration testing. Developed deep learning models using time-series sensor data for anomaly detection and residual life prediction in coolant pump systems.

Utilized Realdisp and PowerBI to analyze Komatsu off-road vehicle data to support a case study with a cross-functional team that identified methods to save 9 liters/hour of fuel on a 60-ton dump truck.

• Completed master’s thesis on the topic “Identification of the structural dynamic design elements through the topology optimization of housing components in electrified powertrains to improve the NVH behavior” earning a 1.0 grade. • Executed research project on topic “Identified key sensitive parameters influencing the NVH behavior of an electrical machine using eFAST and Morris Method” with 1.7 grade.