Application of Multiple Linear Regression and Artificial Neural Networks for the Prediction of the Packing and Capsule Filling Performance of Coated and Plain Pellets Differing in Density and Size

Abstract

Plain or coated pellets of different densities 1.45, 2.53, and 3.61 g/cc in two size ranges, small (380-550 µm) and large (700-1200 µm) (stereoscope/image analysis), were prepared according to experimental design using extrusion/spheronization. Multiple linear regression (MLR) and artificial neural networks (ANNs) were used to predict packing indices and capsule filling performance from the "apparent" pellet density (helium pycnometry). The dynamic packing of the pellets in tapped volumetric glass cylinders was evaluated using Kawakita's parameter a and the angle of internal flow θ. The capsule filling was evaluated as maximum fill weight (CFW) and fill weight variation (FWV) using a semi-automatic machine that simulated filling with vibrating plate systems. The pellet density influenced the packing parameters a and θ as the main effect and the CFW and FWV as statistical interactions with the coating. The pellet size and coating also displayed interacting effects on CFW, FWV, and θ. After coating, both small and large pellets behaved the same, demonstrating smooth filling and a low fill weight variation. Furthermore, none of the packing indices could predict the fill weight variation for the studied pellets, suggesting that the filling and packing of capsules with free-flowing pellets is influenced by details that were not accounted for in the tapping experiments. A prediction could be made by the application of MLR and ANNs. The former gave good predictions for the bulk/tap densities, θ, CFW, and FWV (R-squared of experimental vs. theoretical data >0.951). A comparison of the fitting models showed that a feed-forward backpropagation ANN model with six hidden units was superior to MLR in generalizing ability and prediction accuracy. The simplification of the ANN via magnitude-based pruning (MBP) and optimal brain damage (OBD), showed good data fitting, and therefore the derived ANN model can be simplified while maintaining predictability. These findings emphasize the importance of pellet density in the overall capsule filling process and the necessity to implement MLR/ANN into the development of pellet capsule filling operations.

Enteric Release Essential Oil Prepared by Co-Spray Drying Methacrylate/Polysaccharides—Influence of Starch Type

“…However, although the last two indices are easily determined, they describe only two states of the powder bed at the beginning and at the end of the packing process. As a result of this, when powders of similar particle size are compared, they may not be sensitive enough to detect the differences [ 44 ]. For example, in Table 4 , the differences in Hausner or CC% values among products of different starch grade that belong to the PSC (SD-ADA 0_100 , SD-SOS1 0_100 , SD-SOS30_100) or to the PLM/PSC group (SD-ADA 80_20 , SD-SOS1 80_20 , SD-SOS3 80_20 ) are within the experimental error.…”

Powder Processing in Pharmaceutical Applications—In-Depth Understanding and Modelling

“…The contributions in this Special Issue address powder processing in granulation [1,2], capsule filling [3], tableting [4][5][6][7], and along whole process chains [8], which powders mostly experience in industrial applications. Furthermore, articles span the application depths from scaling from lab to production scale [1,4] and transforming suspensions into dry products [2,8], over in-depth description of sub processes on rotary presses, which depend on powder properties [5][6][7], to statistical experimental design [1,3] and application of artificial neural networks [3].…”

“…Capsule filling with uncoated and coated pellets of different sizes and densities is studied to develop and compare models based on design of experiments and artificial neural network approaches [3]. In this case, artificial neural networks outperform multiple linear regression approaches by far in the prediction of many parameters, e.g., the practically highly relevant fill weight variation.…”