基于稳定映射与深度学习的铣削颤振在线监测方法及系统

By combining stable mapping with deep learning, the shortcomings of feature extraction and model recognition in milling chatter monitoring are solved, realizing high-precision and robust online monitoring of milling chatter, adapting to complex working conditions and possessing clear physical interpretability.

CN122241135BActive Publication Date: 2026-07-17HUNAN UNIV OF SCI & TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUNAN UNIV OF SCI & TECH
Filing Date
2026-05-22
Publication Date
2026-07-17

Smart Images

  • Figure CN122241135B_ABST
    Figure CN122241135B_ABST
Patent Text Reader

Abstract

本发明涉及机加工检测技术领域，尤其涉及一种基于稳定映射与深度学习的铣削颤振在线监测方法及系统，方法包括以下步骤：建立铣削动力学模型，获取模态实验参数，绘制铣削颤振稳定性叶瓣图；开展铣削实验，计算每个参数点到铣削颤振稳定性边界的稳定裕度；为每个实验铣削参数赋予对应的颤振状态标签值；得到实验多维颤振特征向量，对模型进行训练，得到训练好的颤振识别模型；在实际加工中，实时采集原始振动信号，把实时多维颤振特征向量输入颤振识别模型，输出实时的铣削颤振状态在线监测结果。该种基于稳定映射与深度学习的铣削颤振在线监测方法及系统具备明确物理意义、高精度和高鲁棒性，为较佳的工程化解决方案。
Need to check novelty before this filing date? Find Prior Art