fault-classification

Implement GANs to generate time-series signals for imbalanced learning problem. The experiments are conducted using CWRU bearing data.

Multiclass bearing fault classification using features learned by a deep neural network.

ANN based electrical fault detection and classification using line and phase currents and voltages.

EngineFaultDB: A Novel Dataset for Automotive Engine Fault Classification and Baseline Results [IEEE Access]

predictive-maintenance-fault-classification(CWRU data)-and-remaining-useful-life(NASA’s Turbofan Engine )

"The urban building rooftop photovoltaic dataset" is a deep learning dataset designed for studying photovoltaic systems installed on rooftops of urban buildings.

Hybrid CNN-LSTM deep learning model for electrical fault classification in power transmission lines. Achieves 78% accuracy across 6 fault types using time-series analysis. Includes complete ML pipeline with preprocessing, training, and evaluation tools. Built with TensorFlow & Keras.

Contains code for Adaptive protection platform in Smart grids

An anomaly detection software that utilized the data collected from laser sensors to identify abnormal behavior in the kneading machine. The software utilizes a large dataset of kneading machine operation logs and dough thickness measurements to identify normal patterns of operation.

An end-to-end machine learning pipeline for automated optical fibre fault detection, classification, and analysis using OTDR (Optical Time Domain Reflectometer) data.

A multi-agent, real-time monitoring and analytics platform for electrical substations, built for L&T. The system integrates OpenDSS-based power grid simulation, JADE multi-agent communication, Apache Cassandra time-series storage, and Streamlit dashboards to enable live substation oversight, fault diagnostics, and AI-driven load forecasting.

Code and reproducibility artifacts for “Deep Learning Architectures for Fault Analysis in Power System Protection: A Reproducible Evaluation on Public Waveform Data”

Code for the EUSIPCO 2025 paper "Impact of Data Sparsity on Machine Learning for Fault Detection in Power System Protection". Quantifies how relay and bus failures, downsampling, missing voltage/current channels and communication dropouts degrade fault detection and fault line identification.

Detecção, classificação e localização de faltas em linhas de transmissão a partir de simulações ATP/ATPDraw, usando atributos físicos e machine learning. Projeto de Iniciação Científica (PIBIC) — UFPI.

End-to-end Azure ML pipeline for NLP fault classification in industrial maintenance logs | Docker · Azure · Power BI

Companion code for our IJEPES framework paper | ML fault classification & localization on PROTECT-90, one frozen protocol, evidence for every number.

HTTP fault classification with retryable semantics on top of resty-based requests

My application paper and poster for IDA26 PhD Forum, titiled as "Banality of Failure".