Solar Panel Fault Detection Using Deep Learning: A Computer Vision Approach This project presents an automated system for detecting and classifying faults in solar panels using state-of-the-art deep learning and computer vision techniques. Leveraging an EfficientNetB0-based architecture, the model accurately identifies six categories of faults: bi

Custom-trained YOLOv11 model for industrial fault detection in manufacturing environments.

Remote monitoring proof of concept using Viam Robotics for a Stäubli CS9 robot arm with Apera AI vision in harsh industrial environments. Demonstrates real-time fault detection and alerting across PLCs, vision systems, and robot controllers.

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.

Electrical diagnostics utility for analysing 230V RMS voltage behaviour and detecting instability patterns.

A ROS 2 multi-node health monitoring system demonstrating real-time state estimation, fault detection, and telemetry logging in autonomous distributed systems. Implements the Sense-Think-Act architecture pattern with full Docker containerization.Built as a learning project

Sump pump abnormal operation detection, maintenance needed alerts, and energy monitor.

DS Project: A fault-tolerant distributed key-value store using the Raft consensus algorithm

UAV propeller fault detection using 1D-CNN, FFT, Stacked LSTM for RUL prediction. ROS2 real-time diagnostics. 98.4% accuracy.

This repository implements an unsupervised anomaly detection framework based on autoencoder architectures for time series data.

The relabeled triple-classified dataset for ball screw defects used in the journal paper “Domain-unique group- and its subgroups-aware fault diagnostics for machine components: An open-set domain adaptation approach”

Code, configuration templates, and documentation for the "Deep Learning Models for Fault Analysis in Power System Protection" paper

Production-ready ML/AI HVAC monitoring system with real-time simulation, fault detection, and session persistence

A wrapper for connecting to Ecorithm's API Platform through Python

Fault Detection System Development at eParampara Technologies (Test Repo)

Algorithms from my Master's dissertation on fault detection through statistical and machine learning techniques.

This repository contains the implementation of a study that addresses operational challenges in wind turbine fault detection by comparing static thresholds (ISO 10816-21) with a hybrid unsupervised machine learning model using Variational Autoencoder (VAE) and Isolation Forest (IF).

Open-source framework for detecting Silent Data Corruption (SDC) in production GPU/accelerator clusters

mutation testing techniques comparison w.r.t. fault detection.

A framework for Inter-turn fault detection in transformers using wavelet analysis and deep learning