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 th… Show more
“…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):…”
Section: Radial Basis Function Networkmentioning
confidence: 99%
“…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.…”
Section: Models Developmentmentioning
confidence: 99%
“…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.…”
Purpose
The purpose of this research paper is to investigate and model the fused deposition modelling (FDM) process to predict the mechanical attributes of 3D printed specimens.
Design/methodology/approach
By exploiting the main effect plots, a Taguchi L18 orthogonal array is used to investigate the effects of such parameters on three mechanical attributes of the 3D printed specimens. A radial-based integrated network is then developed to map the eight FDM parameters to the three mechanical attributes for both PEEK and PEKK. Such an integrated network maps and predicts the mechanical attributes through two consecutive phases that consist of several radial basis functions (RBFs).
Findings
Validated on a set of further experiments, the integrated network was successful in predicting the mechanical attributes of the 3D printed specimens. It also outperformed the well-known RBF network with an overall improvement of 24% in the coefficient of determination. The integrated network is also further validated by predicting the mechanical attributes of a medical-surgical implant (i.e. the MidFace Rim) as an application.
Originality/value
The main aim of this paper is to accurately predict the mechanical properties of parts produced using the FDM process. Such an aim requires modelling a highly dimensional space to represent highly nonlinear relationships. Therefore, a radial-based integrated network based on the combination of composition and superposition of radial functions is developed to model FDM using a limited number of data points.
“…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):…”
Section: Radial Basis Function Networkmentioning
confidence: 99%
“…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.…”
Section: Models Developmentmentioning
confidence: 99%
“…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.…”
Purpose
The purpose of this research paper is to investigate and model the fused deposition modelling (FDM) process to predict the mechanical attributes of 3D printed specimens.
Design/methodology/approach
By exploiting the main effect plots, a Taguchi L18 orthogonal array is used to investigate the effects of such parameters on three mechanical attributes of the 3D printed specimens. A radial-based integrated network is then developed to map the eight FDM parameters to the three mechanical attributes for both PEEK and PEKK. Such an integrated network maps and predicts the mechanical attributes through two consecutive phases that consist of several radial basis functions (RBFs).
Findings
Validated on a set of further experiments, the integrated network was successful in predicting the mechanical attributes of the 3D printed specimens. It also outperformed the well-known RBF network with an overall improvement of 24% in the coefficient of determination. The integrated network is also further validated by predicting the mechanical attributes of a medical-surgical implant (i.e. the MidFace Rim) as an application.
Originality/value
The main aim of this paper is to accurately predict the mechanical properties of parts produced using the FDM process. Such an aim requires modelling a highly dimensional space to represent highly nonlinear relationships. Therefore, a radial-based integrated network based on the combination of composition and superposition of radial functions is developed to model FDM using a limited number of data points.
“…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.…”
A novel way of integrating the genetic algorithm (GA) and the analytic network process (ANP) is presented in this paper in order to develop a new warehouse assessment scheme, which is developed through various stages. First, we define the main criteria that influence a warehouse performance. The proposed algorithm that integrates the GA with the ANP is then utilized to determine the relative importance values of the defined criteria and sub-criteria by considering the interrelationships among them, and assign strength values for such interrelationships. Such an algorithm is also employed to linguistically present the relative importance and the strength of the interrelationships in a way that can circumvent the use of pairwise comparisons. Finally, the audit checklist that consists of questions related to the criteria is integrated with the proposed algorithm for the development of the warehouse assessment scheme. Validated on 45 warehouses, the proposed scheme has been shown to be able to identify the warehouse competitive advantages and the areas where more improvements can be achieved.
“…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].…”
This paper investigates the Angle of Repose (AoR) of powder materials with respect to their morphological and rheological properties. Glass beads, sand, flour and semolina of different particle sizes were used as the experimental materials. The investigated material was analysed with respect to particle shape and size. The rheological properties of the material were obtained by a shear cell test. The AoR was analysed in terms of cohesion, bulk density, particle size and circularity. More cohesive materials such as the flour samples exhibited the largest AoR > 40°, indicating their poor flowability. Glass bead samples with a high circularity value had significantly lower AoR than the flour. The Angle of Internal Friction values were not dependent on those of the AoR. Using a dimensional analysis, a mathematical model was developed to determine the AoR values based on the material properties. By the application of this model, highly accurate calculation of the value of AoR is made possible.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.