Manufacturing Analytics (Quality & Energy Optimization)
1. The Problem
Roasting processes relied on delayed quality checks and operator experience. Operators often discovered quality issues hours later, after large volumes were already in process. Environmental variability (humidity, seasons), raw material variation (moisture content), and uncontrollable factors led to inconsistent quality, high waste, and elevated energy use.
2. The Solution:
Leveraged existing GE Historian time-series data, MES event data, and new process sensors. Data was modeled by a data scientist to create predictive analytics around roaster performance and final product color.
FrameworX dashboards delivered predictions in real time, recommending operator adjustments or enabling automated control. The models accounted for controllable variables (burner levels, belt speeds, airflow) while recognizing uncontrollable conditions.
Technical Specifications:
ERP: Microsoft D365 (Cloud)
MES: GE Plant Applications
Historian: GE Proficy Historian (time-series data for analytics)
Front End: Tatsoft FrameworX (dashboards for predictive and prescriptive analytics)
PLCs: Rockwell Automation
Integration: Process sensors, quality lab results, historian, MES events
3. Key Enablers:
Predictive analytics applied to historian + MES event data
FrameworX dashboards integrated real-time model outputs
Automated prescriptive recommendations for operators
Continuous improvement through iterative model refinement
4. The Results:
Improved first-pass quality by 10–15%
Reduced waste by ~5% and product downgrades by ~10%
Achieved 10–15% energy cost savings through optimized roasting operation
Reduced schedule disruptions by stabilizing product consistency