Category: CBM Portfolio Project
-
Deploying a Real-Time CBM Dashboard: End-to-End Pipeline with Alerts and Visualization
Building a production-ready CBM dashboard with Flask, TimescaleDB, and Slack alerts. Full pipeline from sensor ingestion to real-time RUL visualization.
-
Training and Evaluating RUL Prediction Models: From Classical ML to LSTM Networks
Random Forest beats vanilla LSTM for RUL prediction in offline benchmarksโbut LSTMs dominate in real-time streaming inference. Here's when to use each.
-
Feature Engineering for Predictive Maintenance: Extracting Health Indicators from Vibration and Temperature Data
Building health indicators from vibration and temperature data for RUL prediction. Time-domain, frequency-domain, and thermal features that actually work.
-
Building a Condition-Based Maintenance System from Scratch: Sensor Data Collection and Preprocessing
Real-world sensor data collection for condition-based maintenance: trigger-based logging, timestamp synchronization, and preprocessing pipeline design.