From OT Data Challenges to AI-Driven Operations on
summary
Shows a production deployment that collects OT time series from eight plants using Litmus at the edge, ships contextualized data into AWS IoT SiteWise, links SAP and lab records, and builds a knowledge graph and symbolic rules for asset failure modes. Demonstrates an automated RCA pipeline that flags anomalies, ranks three root causes, generates evidence-backed reports and work orders, and reports live production impact and energy optimization across six plants and one distillery.
AI-written summary · about
chapters (10)
- 0:00Introduction and welcome
- 1:28OT data challenges overview
- 2:33Distillery-specific complexities
- 3:36Solution architecture with Litmus
- 6:22Demo introduction and foundation
- 7:48Knowledge graph for asset context
- 9:12Symbolic AI for failure modes
- 10:16Automated RCA demonstration
- 13:26AI chatbot and what-if scenarios
- 14:29Customer outcomes and closing
related talks
36mHarnessing the Full Potential of IoT Data with AWS
29mUnleash the power of real-time data
49mReinvent operations and the digital transformation playbook
20mOvercoming AI implementation hurdles: EOT.ai's collaborative approach
20mAutomating Data Science for the IOT
30mCustomer centricity in manufacturing with operational improvements
29mML-Powered IoT: From Warehouse Data to Prod Intelligence in Real Time
29mFrom Data to Decisions: How IoT and Agentic AI Are Transforming Industry