Vidhya Sathish

Papers

Total Citations

H-Index

About

Vidhya Sathish is a researcher specializing in predictive maintenance, fault detection, and prognostics for industrial robotic systems. Her work sits at the intersection of machine learning, signal processing, and industrial automation, with a particular focus on developing data-driven approaches to anticipate and identify mechanical failures before they cause costly downtime. Her most impactful contribution, "Training Data Selection Criteria for Detecting Failures in Industrial Robots" (2016, 16 citations), investigates how the source and composition of training data influence the accuracy of failure detection models using Principal Component Analysis (PCA). By analyzing field data across multiple robots performing varied tasks, she provided practical guidance for engineers building real-world diagnostic systems. Her earlier work established the theoretical groundwork, with "Event Based Robot Prognostics Using Principal Component Analysis" (2014) introducing PCA-driven frameworks for failure prediction in complex industrial environments, and her simulation-based study (2015) demonstrating how joint wear can be modeled and localized using the MATLAB robotics toolbox. Collectively, Sathish's research bridges the gap between theoretical fault detection methodologies and their practical deployment in manufacturing settings, offering valuable insights for industries seeking to optimize maintenance schedules and extend the operational lifespan of robotic systems.