Data comes from a MSc thesis project and consists of 216 samples of granules in glass vials analysed by NIR. You can download the thesis here (download). A downscaled dry granulation process was developed during the project and designed such that three quality attributes variances could be controlled:
Model API concentration (Bovine Serum Albumin, BSA). Six levels ranging from 2% to 15% w/w
Particle size. Three levels, controlled by material mass used during compaction (1 g, 1.5 g and 2 g).
Moisture content. Four levels, controlled using desiccators with relative humidity ranging from 11% to 62%.
Triplicates were produced of each attribute combination. Each sample was measured three times using a Bruker MPA II NIR equipment with resolution 8 cm-1, 64 scans and in the spectral range 11550 cm-1 to 3950 cm-1 for each measurement. The samples were measured before and after moisturization and two datasets were created. Both datasets are available:
Please see dataset called Granules_NIR_data_ambient_moisture and API references Granules_API_reference_ambient_moisture.
After moisture control using desiccators:
Please see dataset called Granules_NIR_data_moisture_controlled and API references Granules_API_reference_moisture_controlled.
The datasets contain the following classes:
Batch ID (example: RH11p0_API02p00_RW1p0)
Consisting of RH (Relative Humidity); API (API concentration) and RW (Riblet wieght) attributes.
Relative humidity [%]*
API concentraiton [%]
Riblet mass [g]
*: Not relevant and therefore not included for the dataset Granules_API_reference_ambient_moisture.