SVR-based analysis on tribological property of ultra high molecular weight polyethylene composites filled with nano-ZnO particles

Abstract

This study develops support vector regression (S VR) models for describing the complex nonlinear relationship between tribological properties (friction coefficient and wear rate) and experimental factors including load, content of filled nanoparticles and speed of relative sliding for the ultra high molecular weight polyethylene composites filled with nano-ZnO particles (UHMWPE/nano-ZnO). The particle swarm optimization (PS O) algorithm is employed for optimizing the parameters of S VR models and obtaining the optimal process parameters for preparing UHMWPE/nano-ZnO. The comparison of results achieved by S VR and multivariable linear regression (MLR) exhibits the superior simulation accuracy and generalization performance of the S VR approach. Meanwhile, multifactor analysis is adopted for investigation on the significances of each experimental factor and their influences on the tribological properties of UHMWPE/nano-ZnO.This study suggests that the S VR is an efficient and novel approach in development of the UHMWPE/nano-ZnO with lower friction coefficient and perfect wear resistance.

Modelling and optimization of nanovector synthesis for applications in drug delivery systems

“…AI algorithms used for modelling are increasing in popularity because due to the lack of variable assumptions, these methods are less restrictive and are capable of recognizing and modelling non-polynomial relations between the variables [18]. Examples of AI used for NV synthesis include multilayer perceptron artificial neural networks (MLP-ANN) [19][20][21], adaptive neurofuzzy inference system (ANFIS) [22], support vector machines (SVMs) [23,24], genetic proggraming (GP) [25,26], decision trees [27], and random forests (RF) [28,29].…”

“…Metaheuristic algorithms that have been used in processes involving nanomaterials are: genetic algorithms (GA) [31][32][33], particle swarm optimization (PSO) [22,24,34], simulated annealing (SA) [35], differential evolution (DE) [36,37], ant colony optimization (ACO) [38], bees algorithm (BA) [39], firefly algorithm (FA) [40], cuckoo search (CS) [41], bat algorithm [42], gravitational search algorithm (GSA) [43] , symbiotic organism search (SOS) [44], whale optimization algorithm (WOA) [45] and grasshopper optimization algorithm (GOA) [45]. Deciding which algorithm to use is no easy task because the no free lunch theorem for optimization states that algorithms which perform better for certain optimization problems will have a lower performance for other class of problems, and therefore there is no overall best algorithm [46].…”