Category: CBM/PHM
-
Deploying RUL Models: Optimization and PHM Integration
Deploy RUL models without crashing production: quantization cuts inference from 45ms to 8ms. Real metrics, optimization code, and PHM integration.
-
RUL Prediction in Python: Linear Regression to LSTM
Build bearing RUL prediction in Python: linear regression baseline to LSTM with NASA C-MAPSS data. Full code, degradation features, performance.
-
PHM Intro: What Is RUL Prediction? Concepts to Data Prep
RUL prediction 101: formulate the problem, engineer degradation features from sensor data, and prepare NASA C-MAPSS dataset for model training.
-
Attention-Based Sensor Fusion: 15% Better Pump Failure Prediction
Fusing vibration, temperature, and current sensors with Attention boosted pump failure prediction from 79% to 94.2% โ here's the architecture.
-
Envelope Analysis vs FFT for Bearing Fault Detection
Envelope analysis caught inner race faults FFT missed โ then nearly failed on outer race. Why band selection breaks or saves your diagnosis.
-
DTW for Multi-Sensor Anomaly Detection in Machinery
DTW beats point-based methods for gradual bearing faults: 12% earlier detection on real degradation data. Includes multi-sensor code.
-
Real-Time CBM Dashboard: Pipeline with Alerts and Viz
Deploy a CBM dashboard with Flask + TimescaleDB + Slack alerts. Full pipeline from sensor stream to RUL predictions in under 200ms.
-
RUL Prediction: Classical ML vs LSTM Training Guide
Random Forest beat LSTM by 12% MAE in offline testsโbut LSTMs won in streaming inference. Here's the benchmark data and when to use each.