The article presents possibility of defects detection from milling time series using nonlinear methods: recurrence plots and recurrence quantifications. The defects are modeled as the holes with different diameters and depths. This allows estimation of the minimal size of defect possible to detect. Based on the conducted research, it has been shown that some of the recurrence indicators enable detection of defects. These recurrence indicators have been tested on the reals damage. Additionally, we show influence of the defect depth on the recurrence indicator values.

中文翻译：

---

复合铣削过程中切削力时间序列的递归分析缺陷检测

本文提出了使用非线性方法从铣削时间序列中检测缺陷的可能性：递归图和递归量化。缺陷被建模为具有不同直径和深度的孔。这允许估计可能检测到的最小缺陷尺寸。根据所进行的研究，已经表明一些重复指标能够检测缺陷。这些重复指标已经过真实损坏的测试。此外，我们展示了缺陷深度对重复指标值的影响。