Machine chatter is still an unresolved and challenging issue in the milling process, and developing an online chatter identification and process monitoring system towards smart manufacturing is an urgent requirement. In this paper, two indicators of chatter detection are investigated. One is the real-time variance of milling force signals in the time domain, and the other one is the wavelet energy ratio of acceleration signals based on wavelet packet decomposition in the frequency domain. Then, a novel classification concept for vibration condition, called slight chatter, is proposed and integrated successfully into the designed multi-classification support vector machine (SVM) model. Finally, a mapping model between image and chatter indicators is established via a distance threshold on the image. The multi-SVM model is trained by the results of three signals as an input. Experiment data and detection accuracy of the SVM model are verified in actual machining. The identification accuracy of 96.66% has proved that the proposed solution is feasible and effective. The presented method can be used to select optimized milling parameters to improve machining process stability and strengthen manufacturing system monitoring.

在铣削过程中，机器颤动仍然是一个尚未解决且具有挑战性的问题，开发面向智能制造的在线颤动识别和过程监控系统是当务之急。本文研究了颤动检测的两个指标。一种是时域铣削力信号的实时方差，另一种是频域中基于小波包分解的加速度信号的小波能量比。然后，提出了一种新的振动条件分类概念，称为轻微震颤，并将其成功集成到设计的多分类支持向量机（SVM）模型中。最后，通过图像上的距离阈值建立图像和颤动指示器之间的映射模型。通过将三个信号的结果作为输入来训练multi-SVM模型。在实际加工中验证了SVM模型的实验数据和检测精度。识别率达到96.66％，证明了该方案的可行性和有效性。提出的方法可用于选择优化的铣削参数，以提高加工过程的稳定性并加强制造系统的监控。