冠状动脉支架轴向缩短力学性能优化设计研究

Research on Optimal Design of Stent Foreshortening Mechanical Property

优秀的轴向缩短性能即低的轴向缩短率已经成为新一代冠脉支架所应拥有的很重要的一个特征。针对支架结构优化设计的复杂性,提出综合应用径向基函数神经网络(RBFNN)和遗传算法(GA)优化支架的轴向缩短性能。结合有限元模拟技术和径向基函数神经网络的方法,建立了轴向缩短率和支架结构设计参数之间的非线性映射模型。把映射模型作为目标函数,应用遗传算法进行优化,使得支架的轴向缩短率达到最小,从而形成一套适应性很强的高效优化方法。结果表明,该方法能够取得高精度的响应面近似模型,并且使支架缩短性优化计算耗时大为减少,优化效率大大提高。

Excellent mechanical property of shortening or low shortening rate has become an essential feature of new coronary stents.In view of the complexity of stent structure optimization,it presents an integrated approach using radial basis function neural network（RBFNN）and genetic algorithm（GA）for foreshortening optimization of stent.Finite element simulation and RBFNN are used to establish the complex non-linear mapping relationship between foreshortening and stent design parameters.RBFNN model is used as an objective function and GA is employed for arriving at optimum configuration of the stent by minimizing the foreshortening.The optimization results illustrate that it can achieve highly accurate response approximation model.And the approach can greatly save the computation time of stent foreshortening optimization and raise the efficiency of optimization process.