DosePI: A Comprehensive Dataset for Peristaltic Pump Accuracy Enhancement in Pharmaceutical Environments

This dataset contains approximately 150,000 peristaltic pump dosing measurements spanning volumes from 0.1 to 2.0 ml, collected using a Flexicon PD12 peristaltic pump system used in pharmaceutical manufacturing environments. The data is structured into two main categories: a core performance dataset and a compensated dataset. The core performance dataset includes baseline performance measurements across four target volumes (0.2, 0.3, 1.2, and 2.0 ml), raw dosing data with calibration points marked, and comprehensive metadata about system configuration and operating conditions. The compensated dataset contains data from multiple compensation strategies. Each compensation sequence includes both uncompensated and compensated phases, with full records of model predictions and resulting dispensed volumes. The dataset captures both statistical (ARIMA) and AI-based (GRU) compensation strategies, documenting improvements achievable through these techniques. Calibration history and system parameters are included as metadata. This represents the first publicly available dataset documenting peristaltic pump behavior across such a wide range of volumes, making it a valuable resource for research in pharmaceutical manufacturing processes and precision dosing systems. All data is provided in standard CSV format, with clear documentation of data structure and experimental conditions. The dataset supports research in dosing system optimization and compensation algorithm development.