Optimal design of a 3D-printed scaffold using intelligent evolutionary algorithms
Applied Soft Computing(2016)
摘要
The aggregated artificial neural network was used to investigate the simultaneous effects of printing parameters on the compressive strength and porosity of scaffolds.Particle swarm optimization algorithm was implemented to obtain the optimum topology of the AANN. Pareto front optimization was used to determine the optimal setting parameters.The presented results and discussion can give informative information to practitioners who want to design a porous structure, and need to know the impact of influential design parameters. Fabrication of three-dimensional structures has gained increasing importance in the bone tissue engineering (BTE) field. Mechanical properties and permeability are two important requirement for BTE scaffolds. The mechanical properties of the scaffolds are highly dependent on the processing parameters. Layer thickness, delay time between spreading each powder layer, and printing orientation are the major factors that determine the porosity and compression strength of the 3D printed scaffold.In this study, the aggregated artificial neural network (AANN) was used to investigate the simultaneous effects of layer thickness, delay time between spreading each layer, and print orientation of porous structures on the compressive strength and porosity of scaffolds. Two optimization methods were applied to obtain the optimal 3D parameter settings for printing tiny porous structures as a real BTE problem. First, particle swarm optimization algorithm was implemented to obtain the optimum topology of the AANN. Then, Pareto front optimization was used to determine the optimal setting parameters for the fabrication of the scaffolds with required compressive strength and porosity. The results indicate the acceptable potential of the evolutionary strategies for the controlling and optimization of the 3DP process as a complicated engineering problem.
更多查看译文
关键词
Scaffolds,3D printer,Aggregated artificial neural network (AANN),Particle swarm optimization (PSO),Porous structure,Mechanical strength
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络