基于GA—NN人体心血管模型FDM制造的工艺参数优化

发布时间：2018-06-06 02:22

本文选题：人体心血管模型 + D打印　；参考：《激光杂志》2017年08期

【摘要】：基于熔融沉积成型(Fused Deposition Modeling,FDM)的3D打印技术而制作的人体心血管模型,是批量制作透明人体心血管模型的母模,其制作步骤是:利用三维激光扫描技术和逆向工程软件来反求重构模型;将模型切片后导入到桌面FDM设备采用默认参数打印出实体模型。针对默认工艺参数下模型出现的破损缺陷,采用参数优化的方式改善缺陷。以心血管模型破损面积(mm2)为目标,利用正交试验数据建立了反应其与分层厚度(d/mm),喷头温度(T/℃)和填充速率(C/mm/s)之间关系的神经网络(Neural Network,NN)模型。采用遗传算法(Genetic Algorithm,GA)方法对上述工艺参数,进行优化并得到相应的制造参数。通过实验验证,结果表明:采用优化后的工艺参数,模型的预期破损面积(0.021mm2)与实验结果(0.023mm2)相符合,并且小于之前的试验结果。故采用GA-NN对人体心血管模型FDM制造进行优化是可行的。
[Abstract]:The human cardiovascular model, which is based on the 3D printing technology of fused Deposition Modeling (FDM), is the master model for mass production of transparent human cardiovascular model. The manufacturing steps are as follows: 3D laser scanning technology and reverse engineering software are used to reverse reconstruct the model, and then the model is sliced and imported into the desktop FDM device to print out the solid model by default parameters. Aiming at the damage defect of the model under the default process parameters, the defect is improved by the method of parameter optimization. Taking the damaged area of cardiovascular model as a target, a neural network (NN) model was established based on the orthogonal test data, which reflected the relationship between the model and the stratified thickness of D / mm, nozzle temperature (T / C) and filling rate (C / mm / s). Genetic algorithm (GA) is used to optimize the process parameters and obtain the corresponding manufacturing parameters. The experimental results show that the predicted damage area of the model is 0.021 mm ~ 2) which is in agreement with the experimental result (0.023 mm ~ 2), and is smaller than that of the previous test results. Therefore, it is feasible to optimize the manufacture of human cardiovascular model FDM by GA-NN.
【作者单位】：重庆大学机械工程学院;重庆市人民医院;重庆市光学机械研究所;
【基金】：重庆市科委应用开发项目(cstc2013yykf A10014)
【分类号】：R318.1;TP391.73

【相似文献】