How Does Data Science Revolutionize the World of Machines?
summary
A ship‑engine sound‑classification and predictive maintenance project builds a model that predicts remaining useful life using time series regression and feature engineering rather than hand‑coded physics rules. It starts from sound sensors, struggles with 21 sensors per engine and sensor restrictions, addresses class imbalance and trains on public NASA data that shows 100 Space Shuttle engines 4 needed attention. Workflows include on‑vessel testing, hackathons to create ML skills, deployments on noncritical engines, and lessons from Siemens Deutsche Bahn ICE pilots.
AI-written summary · about
chapters (10)
- 0:00Start
- 14:03SENSORS
- 15:21TIME SERIES DATA
- 16:03MODEL SELECTION
- 17:31FEATURE ENGINEERING
- 18:44CLASS BALANCE
- 19:42PRECISION & RECALL
- 20:29ACCURACY
- 21:26DATA AMOUNT
- 21:59ENGINE HEALTH
related talks
32mTesting Machine Learning Systems: What it is and why you should care
20mAutomating Data Science for the IOT
41mData Science – The New Troublemaker in the Delivery Pipeline
14mTransforming Manufacturing: AI-Driven Predictive Maintenance
20mIntelligent Decision Support: Enabling CSM & FSM with Health Monitoring
25mBuilding A Successful Data Science Team
21mHow The Application Of Machine Learning Is Changing The Way Companies Use Data
08mdata science in automotive