Skills you will gain:
About Program:
A fast-paced, 3-day, 90% hands-on program where you’ll build a RoboDK robot cell, stand up an IoT/Digital Twin (OPC UA → MQTT → TSDB), and deploy edge ML for quality, anomaly, and basic RUL. You’ll go from offline programming to live KPIs (OEE, cycle time, energy/unit) with dashboards, alarms, and interlocks. Leave with a working bundle: RoboDK project, twin stack, edge ML services, SOPs, and alert topics—ready to adapt to real energy ops.
Aim: Equip participants to design, connect, and operationalize a full Industry 4.0 pipeline for energy operations—building a RoboDK robot cell, creating a live IoT/Digital Twin, and deploying edge ML for quality, anomaly, and maintenance—so they can go from offline programming to real-time KPIs and actionable decisions.
Program Objectives:
What you will learn?
📅 Day 1 – RoboDK Cells (Offline → Online)
- Concept sprint: Robot cell basics for energy ops (pick-place, torqueing, inspection), safety envelopes, and tool frames
- Build a RoboDK cell (robot + turntable + fixtures) for an energy asset task (e.g., valve assembly or inverter heat-sink placement)
- Calibrate TCP & reference frames; import CAD (STEP) and create targets/paths with collision checks
- Add sensors and IO stubs; map gripper open/close and torque gun signals
- Generate offline programs (UR/KUKA/FANUC post); simulate cycle time & reach; export cycle report
- Create a changeover: parametrize path for two SKUs; save recipe files and a quick SOP
📅 Day 2 – IoT Twins & Edge Connectivity
- Concept sprint: What is an IoT/Digital Twin for a cell/line; OPC UA vs MQTT; time-series stores
- Spin up an OPC UA server for the robot cell (simulated tags: pose, IO, cycle_ok) and browse with a client
- Bridge OPC UA → MQTT; publish twin topics (cell/status, robot/pose, quality/ok) using JSON schema
- Ingest to a time-series DB (InfluxDB/Timescale) and persist recipe/cycle/energy metrics
- Build a lightweight digital twin dashboard (Node-RED/Streamlit): live KPIs (OEE, cycle time, energy per unit), alarm banner, and recipe selector
- Implement edge rules: debounce a sensor, create an interlock (door_open ⇒ robot_hold), and test a “fault → maintenance ticket” webhook
📅 Day 3 – ML Analytics for Quality, Anomaly & Maintenance
- Concept sprint: Framing anomaly vs quality classification vs RUL; labeling and drift
- Build a feature table from Day-2 streams (cycle-level stats, torque traces, robot current, temperature)
- Train a quality classifier (gradient boosting) for pass/fail based on torque/current signatures; interpret using SHAP
- Train an anomaly detector (isolation forest/autoencoder) on robot/IO telemetry and set calibrated alert thresholds
- Estimate Remaining Useful Life (RUL) using survival/Weibull fit for a consumable (gripper pad) with cycle counts and peak force
- Deploy models at the edge (Docker container): subscribe to MQTT, score in real time, publish alerts and update twin dashboard with trends
- Create a runbook: alarm triage, false-positive guardrails, rollback switch; export a one-page “ops playbook”
Mentor Profile
Fee Plan
Get an e-Certificate of Participation!

Intended For :
Robotics & automation engineers (RoboDK/UR/KUKA/FANUC-curious)
OT/Controls engineers & IoT/Edge architects (OPC UA, MQTT)
Data/ML engineers & applied scientists in manufacturing/energy
Production/quality leaders exploring OEE, predictive maintenance
Final-year students & researchers in Robotics/IIoT/AI (project-focused)
Career Supporting Skills
Program Outcomes
-
Build & calibrate a collision-safe RoboDK cell and generate vendor posts.
-
Parameterize changeovers for ≥2 SKUs; export cycle reports, recipes, and an SOP.
-
Stand up OPC UA → MQTT with clear JSON topics/schemas and persist to a TSDB.
-
Build a live digital twin dashboard with KPIs (OEE, cycle time, energy/unit) and alarms.
-
Engineer features, train quality/anomaly/RUL models, and explain via SHAP.
-
Containerize & deploy models at the edge to score in real time and publish results.
-
Implement edge rules (debounce, interlocks, fault→ticket webhook).
-
Deliver a working bundle (cell project, twin stack, ML services, SOPs, alerts, KPIs).

