当前位置: X-MOL 学术IEEE ASME Trans. Mechatron. › 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.)
Generative Adversarial Network for Prediction of Workpiece Surface Topography in Machining Stage
IEEE/ASME Transactions on Mechatronics ( IF 6.1 ) Pub Date : 2020-10-22 , DOI: 10.1109/tmech.2020.3032990
Le Cao 1 , Tao Huang 1 , Xiao-Ming Zhang 2 , Han Ding 1
Affiliation  

Surface topography plays a key role in the service performance of parts, and is often used as a metric for detecting machining states as well. Hence, it is of great importance to online predict the surface topography to avoid surface deterioration and machining faults. However, alternative solutions for this purpose remain to be developed. This article presents a generative adversarial network to predict the statistical distribution of surface topography conditioned on cutting parameters, measured cutting forces, as well as system vibrations. The local dynamic characteristics and global quasi-static trend of measured process quantities are extracted by short-time spectrum technique, then mapped into the local surface features patch by patch. To improve the network performance, we embed several useful tricks, such as recursive residual block, skip connection, and global residual architecture into the surface generator so as to enhance its capacity of learning the complicated nonlinear mapping against limited training data. The model performance is evaluated and validated using the structure similarity index, the distance of extracted features by the visual geometry group network, as well as the perceptual index. The results indicate that the recursive architecture performs better than nonrecursive one on learning the nonlinear correlation between surface topography and measured process quantities. Besides, by applying adversarial learning, the texture characteristics can be well-captured to avoid the blur of high-frequency details.

中文翻译:

生成对抗网络预测加工阶段的工件表面形貌

表面形貌在零件的服务性能中起着关键作用,并且通常也用作检测加工状态的度量。因此,在线预测表面形貌以避免表面变质和加工故障非常重要。但是,为此目的还需要开发其他解决方案。本文提出了一种生成对抗网络,以预测以切削参数,测得的切削力以及系统振动为条件的表面形貌的统计分布。利用短时光谱技术提取了被测过程量的局部动态特征和整体准静态趋势,然后逐块映射到局部表面特征中。为了提高网络性能,我们嵌入了一些有用的技巧,例如递归残差块,跳过连接,并将全局残差架构引入到表面生成器中,从而增强其针对有限的训练数据学习复杂的非线性映射的能力。使用结构相似性指数,视觉几何组网络提取的特征的距离以及感知指数来评估和验证模型性能。结果表明,在学习表面形貌与测得的过程量之间的非线性相关性方面,递归体系结构的性能优于非递归体系。此外,通过进行对抗学习,可以很好地捕获纹理特征,从而避免高频细节的模糊。以及将全局残差架构引入到表面生成器中,以增强其针对有限训练数据学习复杂非线性映射的能力。使用结构相似性指数,视觉几何组网络提取的特征的距离以及感知指数来评估和验证模型性能。结果表明,在学习表面形貌与测得的过程量之间的非线性相关性方面,递归体系结构的性能优于非递归体系。此外,通过进行对抗学习,可以很好地捕获纹理特征,从而避免高频细节的模糊。以及将全局残差架构引入到表面生成器中,以增强其针对有限训练数据学习复杂非线性映射的能力。使用结构相似性指数,视觉几何组网络提取的特征的距离以及感知指数来评估和验证模型性能。结果表明,在学习表面形貌与测得的过程量之间的非线性相关性方面,递归体系结构的性能优于非递归体系。此外,通过进行对抗学习,可以很好地捕获纹理特征,从而避免高频细节的模糊。视觉几何组网络提取的特征的距离以及感知指数。结果表明,在学习表面形貌与测量过程量之间的非线性相关性方面,递归体系结构的性能优于非递归体系。此外,通过进行对抗学习,可以很好地捕获纹理特征,从而避免高频细节的模糊。视觉几何组网络提取的特征的距离以及感知指数。结果表明,在学习表面形貌与测得的过程量之间的非线性相关性方面,递归体系结构的性能优于非递归体系。此外,通过进行对抗学习,可以很好地捕获纹理特征,从而避免高频细节的模糊。
更新日期:2020-10-22
down
wechat
bug