Pallavi Marni

Papers

Total Citations

H-Index

About

Pallavi Marni is a researcher specializing in predictive maintenance and fault diagnostics for rotating machinery, with a particular focus on bearing fault detection using machine learning and deep learning techniques. Her most-cited work, "Bearing Fault Detection Using Comparative Analysis of Random Forest, ANN, and Autoencoder Methods" (2021), has garnered 20 citations, establishing a foundational benchmark for evaluating classical and modern algorithms in industrial anomaly detection. Marni’s key contribution lies in systematically comparing traditional ensemble methods like Random Forest with neural network architectures—including Artificial Neural Networks (ANN) and Autoencoders—to identify optimal approaches for early fault identification in bearings, a critical component in manufacturing and energy systems. Her research bridges the gap between theoretical machine learning models and practical, real-world industrial applications, offering engineers actionable insights for reducing downtime and maintenance costs. By demonstrating the strengths and limitations of each method under varying data conditions, Marni has provided a valuable framework for future work in condition monitoring. Her work is particularly notable for its clarity in methodology and reproducibility, making it a go-to reference for students and researchers entering the field of intelligent fault diagnosis.