A predictive integrated framework based on the radial basis function for the modelling of the flow of pharmaceutical powders

Abstract

This study presents a modelling framework to predict the flowability of various commonly used pharmaceutical powders. The flowability models were trained and validated on 86 samples including single components and binary mixtures. Two modelling paradigms based on artificial intelligence (AI) namely, a radial basis function (RBF) and an integrated network were employed to model the flowability represented by the flow function coefficient (FFC) and the bulk density (RHOB). Both approaches were utilized to map the input parameters (i.e. particle size, shape descriptors and various materials and mixtures) to the flow properties. The input parameters of the blends were determined from the particle size and shape properties of the single components. The results clearly indicated that the integrated network outperformed the single RBF network in terms of the predictive performance and the generalization capabilities. For the integrated network, the coefficient of determination of the testing data set (not used for training the model) for 2 FFC was 2 = 0.93, reflecting an acceptable predictive power of this model. Since the flowability of the blends can be predicted from single component size and shape descriptors, the integrated network can assist formulators in selecting excipients and their concentrations to improve flowability with minimal experimental effort and material. The presented modelling approach can thus be employed instead of actual measurements throughout the process development stage resulting in the (i) minimization of the time required, (ii) exploration and examination of the design space, and (iii) minimization of material waste.

The development of a radial based integrated network for the modelling of 3D fused deposition

“…where m i and s i represent the parameters in terms of the mean and standard deviation of the ith Gaussian function, respectively. The predicted output (y P ) of the RBF network can then be written as a linear combination of such functions as follows (Alshafiee et al, 2019):…”

“…Because of its proven effectiveness and flexibility, the radial basis function (RBF) network has been used in a variety of applications (e.g. engineering and health) (Alshafiee et al , 2019). Figure 8 shows a schematic representation of the RBF network.…”

“…The Gaussian function can be mathematically expressed as follows (AlAlaween et al , 2020): where µ i and σ i represent the parameters in terms of the mean and standard deviation of the i th Gaussian function, respectively. The predicted output ( y P ) of the RBF network can then be written as a linear combination of such functions as follows (Alshafiee et al , 2019): where λ o and λ i represent the bias and the weight of the i th Gaussian function, respectively. Such parameters are usually initialized randomly and then optimized using the back-propagation network.…”

A new framework for warehouse assessment using a Genetic-Algorithm driven analytic network process

“…Data Envelopment Analysis (DEA) was also used to determine the efficiency [ 16 ]. Recently, artificial intelligence models have been included in many applications, such as manufacturing and marine, this being due to their ability to mimic the human cognitive process [ 17 , 18 ]. Such models have also been implemented in the area of logistics and supply chain management to incorporate human expertise.…”

Analysis of Static Angle of Repose With Respect to Powder Material Properties

“…Its value is influenced by interparticle forces (van der Walls), material moisture, particle size and others. The more cohesive the material, the worse flow properties and lower the f f c flow function parameter [26].…”