Energy Consumption Optimization of a Fluid Bed Dryer in Pharmaceutical Manufacturing Using EDA (Exploratory Data...

Area of Science:

• Chemical Engineering
• Process Optimization
• Data Science

Background:

• Fluid bed dryers are crucial for pharmaceutical production, but preheating phases are energy-intensive.
• Preheating time variability is linked to operational factors, not product characteristics.
• Energy efficiency in industrial drying processes is a key sustainability concern.

Purpose of the Study:

• To reduce energy consumption during the preheating phase of fluid bed dryers.
• To optimize the preheating process using sensor data analysis.
• To identify key factors influencing preheating time.

Main Methods:

• Applied Exploratory Data Analysis (EDA) to sensor data from fluid bed dryer trials.
• Analyzed sensor readings to understand process dynamics and identify optimization opportunities.
• Utilized data science methodologies for deriving insights from experimental data.

Main Results:

• Identified an optimal configuration for the fluid bed dryer's preheating phase.
• Achieved an average reduction of one hour in preheating time per batch.
• Quantified energy savings of approximately 18.5 kWh per 150 kg batch.

Conclusions:

• EDA is effective in optimizing industrial processes like fluid bed drying.
• Optimized preheating significantly reduces energy consumption and operational costs.
• Data-driven insights can lead to substantial annual energy savings exceeding 3,700 kWh.