Agni Datta

Papers

Total Citations

H-Index

About

Agni Datta’s research centers on intelligent fault diagnosis and condition monitoring for industrial systems, with a particular focus on robotics and machinery. His major contributions lie in developing automated, generic methods for detecting and classifying faults using advanced machine learning and signal processing techniques. Notably, his 2007 work on unsupervised clustering for fault diagnosis (17 citations) pioneered exploratory data analysis approaches that identify hidden failure patterns without requiring labeled training data, offering a powerful alternative to supervised methods. In his 2006 study on industrial robots (5 citations), Datta integrated support vector machines with discrete wavelet transforms to create a robust, accurate diagnostic framework applicable across various robot types. This work demonstrated how combining time-frequency analysis with classification algorithms could achieve high precision in real-time fault identification. Datta’s research has practical implications for reducing downtime and maintenance costs in manufacturing, and his methods have influenced subsequent studies in predictive maintenance and industrial automation. His ability to bridge theoretical machine learning with real-world engineering challenges marks him as a thoughtful contributor to the field of intelligent diagnostics.