Yuri Winche Achermann

Yuri Winche Achermann

building AI agents for manufacturing

Aachen, Germany

Actions

Aerospace engineer building AI agents for manufacturing plants in Brazil. Former CTO and co-founder of a manufacturing-tech startup in Germany, built a CNC predictive-maintenance system with RWTH and Fraunhofer.

Overall, contributed to projects with NASA Innovative Advanced Concepts and MIT GeneSys, worked with Artefact data consulting, the Fraunhofer Institute for Production Technology (IPT) and the startups later on.

Area of Expertise

  • Business & Management
  • Information & Communications Technology
  • Manufacturing & Industrial Materials

Topics

  • Aerospace
  • Manufacturing & Production
  • Computer Vision
  • AI

MCP on a Unified Namespace to map out a Factory Shop Floor

Factories already publish data: PLC tags over MQTT, OPC UA servers, MTConnect agents, ERP exports. An AI agent pointed straight at that is lost: every plant names the same machine three ways, and "stopped" means something different in each source.

This talk shows how, in production, I give an agent a stable view of each plant through a Unified Namespace organized by the ISA-95 hierarchy, and how that view is served over MCP:
• Normalize before exposing. Source codes map to a canonical state × mode model (OPC UA Machinery, MTConnect), with versioned mappings. Unmapped inputs go to quarantine instead of creating assets.
• Design tools around questions, not tables. Coarse tools such as "losses for this line and period" versus generic query tools: accuracy, cost and latency trade-offs.
• Identity end to end. User → role → plant scope → tenant, enforced in Postgres row-level security.
• Other agents as first-class clients. An external partner agent subscribes to the same namespace over MQTT and calls the same tools under an integration role.
• Raw, canonical, metric. Parquet archive, Postgres + TimescaleDB canonical layer, versioned KPI snapshots, and why the agent only reads the last two.

Takeaways
1. A reference layout for exposing industrial data to agents through MCP.
2. Tool-granularity trade-offs, with examples of good and bad tools.
3. A pattern for letting third-party agents in without opening the database.

oneDAL Under an Industrial AI Agent

The agent's language model that runs for manufacturing plants, never computes losses itself: it calls tools that cluster machine stops, detect cycle-time drift and rank the drivers of lost production, then cites their results.

Those tools run every night for every plant and on demand when someone asks a question, on a CPU-only hardware at the plant edge. That makes CPU efficiency relevant.

This talk shows how the tool layer uses oneDAL through the Intel Extension for Scikit-learn:
• The workloads: DBSCAN and k-means over stop events, nearest-neighbour drift detection on cycle times, random-forest ranking of loss drivers, PCA over multi-signal machine data.
• The integration: patching existing scikit-learn code, what changed and what didn't, and how results are checked against stock scikit-learn before an agent may cite them.
• The numbers: latency per tool call and compute cost per plant per day, stock versus oneDAL, on production plant data (N machines, M events per day).
• The agent side: how fast, deterministic tools change agent design: fewer cached answers, fresher briefings, shorter waits in chat.

Code and a synthetic plant generator are on GitHub, so attendees can reproduce the benchmarks.

Takeaways
1. A pattern for putting oneAPI-accelerated analytics behind an agent's tool interface.
2. Measured speed-ups and cost on a real-shaped manufacturing workload.
3. A reproducible repo to try it on your own data.

Fundamentals of LLM Fine-Tuning Techniques

Join this interactive session to explore popular LLM fine-tuning techniques and boost your AI development skills, helping you stand out on global LLM leaderboards like this one:
`https://huggingface.co/spaces/Intel/powered_by_intel_llm_leaderboard`

AI PC-Powered Drones: Advanced Real-World Applications with Intel’s Latest NUC

This session will delve into the AI capabilities of the newest NUCs when applied into an unconventional environment, integrated directly onboard a drone, showcasing the advancements in edge computing. We’ll explore how the NUC's CPU, GPU, and especially its NPU (Neural Processing Unit) work together seamlessly to optimize AI workloads, enabling real-time data processing and decision-making without relying on cloud connectivity.

Attendees will discover how this compact, high-performance system leverages AI technology to accelerate inference speeds, reduce latency, and boost efficiency. By utilizing Intel’s XPU architecture, the NUC enables versatile, highly responsive AI operations that unlock new possibilities for autonomous navigation, real-time environmental analysis, and enhanced situational awareness—transforming drones into intelligent, adaptable tools for both industrial and recreational use.

Leveraging oneAPI for Industry Application: A Deep Dive focusing on predictive maintenance context

In this session, we will explore how Intel’s oneAPI technology can be directly applied to solve real-world industrial challenges, specifically in the field of predictive maintenance. Using the example of ToolDetective, a cutting-edge predictive maintenance solution for monitoring metal cutting tool wear, we will demonstrate how integrating oneAPI-optimized AI frameworks, GPU acceleration, and advanced data processing techniques can significantly enhance performance and efficiency.

Intel AI DevSummit WorldWide 2025 Sessionize Event

February 2025

oneAPI DevSummit 2024 hosted by UXL Foundation Sessionize Event

October 2024

Yuri Winche Achermann

building AI agents for manufacturing

Aachen, Germany

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top