当前位置: X-MOL 学术J. Grid Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Pilot Applied Physics Grid Computing Infrastructure for Developing Applications Predicting the Qualities of Industrial Coatings
Journal of Grid Computing ( IF 5.5 ) Pub Date : 2021-07-01 , DOI: 10.1007/s10723-021-09566-y
Vasiliy Chitanov , Michael Krieger , Paul Heinzlreiter , Lilyana Kolaklieva , Roumen Kakanakov

A pilot grid computing test infrastructure has been created between the Central Laboratory of Applied Physics (CLAP), part of Bulgarian Academy of Sciences, and RISC Software GmbH, a subsidiary research company of Johannes Kepler University in Austria. The infrastructure is used by specialists in applied physics for training in the application of grid technologies. A specific application has been developed for predicting the qualities of industrial coatings researched at CLAP. “SKLEARN “Python library, including six predictive models, is used by the application. The nanohardness of different coatings is predicted and compared with data from actual measurements for the validation of the modeling results. The results show that of all methods, Gaussian Process Regression (GPR) gives the closest predictions for most of the research coatings.



中文翻译:

用于开发预测工业涂层质量的应用的试点应用物理网格计算基础设施

保加利亚科学院的应用物理中心实验室 (CLAP) 和奥地利约翰内斯开普勒大学的附属研究公司 RISC Software GmbH 之间创建了一个试点网格计算测试基础设施。该基础设施由应用物理学专家用于电网技术应用培训。已经开发了一个特定的应用程序来预测 CLAP 研究的工业涂料的质量。应用程序使用“SKLEARN”Python 库,包括六个预测模型。预测不同涂层的纳米硬度,并与实际测量数据进行比较,以验证建模结果。结果表明,在所有方法中,高斯过程回归 (GPR) 对大多数研究涂层给出了最接近的预测。

更新日期:2021-07-01
down
wechat
bug