Probabilistic predictive control of porosity in laser powder bed fusion
Probabilistic predictive control of porosity in laser powder bed fusion
复制标题
激光粉末床熔合孔隙率的概率预测控制
DOI：
10.1007/s10845-021-01836-6
复制
发表时间：
2021
影响因子：
8.3
通讯作者：
S. Mahadevan
中科院分区：
文献类型：
--
作者：
Paromita Nath;S. Mahadevan
这项工作提出了一种贝叶斯方法，通过将基于物理的模拟与在线监测数据相结合，对增材制造部件进行逐层预测质量控制。该模型和传感器数据首先用于推断印刷层中的孔隙率，预测未来层中的孔隙率，以及调整工艺参数。由于在打印过程中无法直接观察到孔隙率，因此使用监控（使用红外热成像仪）获得的温度曲线来推断成品部件中的孔隙率。首先利用奇异值分解对热图像进行降维，建立了孔隙度推断模型。接下来，在过程控制中，预测最终部件中的孔隙率，并且如果该预测的孔隙率大于期望的阈值，则基于优化来调整用于打印下一层的过程参数。为了确保预测模型的快速和准确，昂贵的有限元模型被替换为代理模型，并使用使用实验数据校准的差异项来校正代理模型预测。根据监测数据对预测模型进行逐层更新，并利用更新后的模型对最终零件的孔隙度进行预测。通过改变激光功率和激光速度等工艺参数，验证了该方法在控制激光粉末床熔合中孔隙率方面的有效性。
This work presents a Bayesian methodology for layer-by-layer predictive quality control of an additively manufactured part by integrating physics-based simulation with online monitoring data. The model and the sensor data are first used to infer porosity in the printed layers, prediction of porosity in future layers, and adjustment of process parameters. Since porosity is not directly observable during the printing process, the temperature profile obtained from the monitoring (using an infra-red thermal camera) is used to infer porosity in the finished part. The porosity inference model is constructed by first reducing the dimension of the thermal images by employing singular value decomposition. Next, in process control, the porosity in the final part is predicted, and if this predicted porosity is more than a desired threshold, the process parameters for printing the next layer are adjusted based on optimization. To ensure that the prediction model is both fast and accurate, the expensive finite element model is replaced by a surrogate model, and a discrepancy term calibrated using experimental data is used to correct the surrogate model prediction. The prediction model is also updated at every layer based on the monitoring data, and the updated model is used to predict the porosity in the final part. The effectiveness of the proposed method is demonstrated for controlling porosity in laser powder bed fusion by changing the process parameters such as laser power and laser speed.
使用激光粉末床熔融制造的薄壁特征的设计规则和现场质量监控
DOI：
10.1115/msec2019-3035
发表时间：
2019
期刊：
Manufacturing Science and Engineering Conference
影响因子：
--
作者：
Gaikwad, Aniruddha;Imani, Farhad;Rao, Prahalad;Yang, Hui;Reutzel, Edward
通讯作者：
Reutzel, Edward
DOI：
10.1115/1.4043798
发表时间：
2019-06
期刊：
Journal of Manufacturing Science and Engineering
影响因子：
--
作者：
Zhuo Wang;Pengwei Liu;Yaohong Xiao;X. Cui;Zhen Hu;Lei Chen
通讯作者：
Zhuo Wang;Pengwei Liu;Yaohong Xiao;X. Cui;Zhen Hu;Lei Chen