Intelligent OT-Data Pipelines - Machines to Clouds
summary
Project Fledge builds six microservices that connect machines and aftermarket sensors, buffer and transform data, run edge analytics (RMS, FFT) and ML inference, and integrate with historians and clouds via plugins. It supports about 100 south protocols, uses PostgreSQL storage, exposes REST APIs, and can run on tiny hardware (Raspberry Pi Zero) or containers. Real deployments push roughly 2.5 million tags a day from MQTT into PI historians, with setpoint writes back to PLCs and hierarchical Fledge-to-Fledge pipelines.
AI-written summary · about
chapters (7)
- 0:00Intro
- 0:33Project Description
- 2:36Industrial Edge
- 6:35FLETCH microservices
- 9:08FLETCH applications
- 11:29Linux in OT
- 12:21QA
related talks
39mCodeless Pipelines With Pulsar and Flink
21mSoftware Best Practices for Data Pipelines: Form Energy's Multi-Day Storage R&D Pipeline 🌳
29mUnleash the power of real-time data
47mBuilding Modern Data Streaming Apps with Open Source
09mFrom Factory Floor to Cloud — Scaling Manufacturing Data on
16mFrom OT Data Challenges to AI-Driven Operations on
45mPractical Cloud Pipelines
28mBuilding a Coud Native Data Pipeline for Your Real-Time ML & AI Apps