一种整体叶盘铣削颤振智能控制方法

By installing multiple sensors during the integral bladed disk milling process and utilizing edge computing and chatter prediction models, real-time chatter monitoring and dynamic feature extraction of the integral bladed disk were achieved. This solved the problems of insufficient real-time performance and accuracy of chatter control in existing technologies, and improved machining accuracy and tool life.

CN120871746BActive Publication Date: 2026-07-17SHENYANG LIMING AERO-ENGINE GROUP CORPORATION

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENYANG LIMING AERO-ENGINE GROUP CORPORATION
Filing Date
2025-07-25
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve real-time, precise chatter control during integral bladed disk milling, leading to machining errors, tool wear, and equipment malfunctions. Furthermore, existing intelligent control technologies fall short in multi-source signal fusion and dynamic feature extraction, making it difficult to meet the precision machining requirements of complex thin-walled parts for aero-engines.

Method used

By installing multiple sensors on the spindle, cutting tool, and impeller clamping parts of CNC machine tools, and combining edge computing terminals and OPC UA protocols, real-time preprocessing and data interaction of multi-source signals are achieved, a chatter prediction model is constructed, multi-signal joint decision-making and early warning are performed, and control commands are output to suppress chatter.

Benefits of technology

It achieves a 40%-60% reduction in milling vibration amplitude, eliminates milling marks on the blade surface, and achieves a surface roughness of Ra0.6μm, thereby improving machining accuracy and tool life.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120871746B_ABST
    Figure CN120871746B_ABST
Patent Text Reader

Abstract

本发明的一种整体叶盘铣削颤振智能控制方法,通过传感器采集多源信号,并提取能反映当前加工状态的特征,然后基于多源动态信号和特征数据构建颤振预测模型;将传感器采集的实时多源动态信号输入预测模型,根据设定阀值用来识别颤振是否将会发生,根据预测结果进行多信号联合决策与预警,输出预警等级;根据预警等级自动调整切削参数,使动态信号降到阀值以内,达到控制整体叶盘薄壁叶片铣削振动的目的。
Need to check novelty before this filing date? Find Prior Art