多传感器信息融合的刀具磨损状态智能监测系统
Intelligent Monitoring System for Tool Wear Based on Multi-sensor Information Fusion
孙巍伟 1黄民 1何一千 1郭中原2
作者信息
- 1. 北京信息科技大学机电工程学院,北京 100192
- 2. 北京遥感设备研究所,北京 100854
- 折叠
摘要
为了提高数控机床刀具磨损状态智能监测的可靠性,提出一种基于多传感器信息融合的刀具磨损状态智能监测方法及系统.利用多种传感器分别采集刀具加工过程中的机床变频器输入电流信号、工件三向振动信号和声信号,然后对采集到的信号进行时域、频域和时频域处理分析.系统自动识别提取出其中与刀具磨损程度相关性较高的敏感特征变量,并利用马氏距离法对敏感特征向量进行分析计算,确定刀具不同状态下的阈值,并据此判断刀具的磨损状态.最后基于上述原理利用QT开发平台研发一套完整的数控机床刀具磨损状态智能监测系统.试验结果表明,该系统能够实时准确地监测出刀具的磨损状态.
Abstract
To improve the accuracy and reliability of intelligent monitoring of tool wear status of CNC machine tools,an intelligent monitoring method and system based on multiple sensors information fusion was proposed.A variety of sensors were used to collect the machine tool inverter input current signals,workpiece three directional vibration signals and acoustic signals during tool machining,then the collected signals were processed and analyzed in the time,frequency and time-frequency domains.The sensitive feature vector varia-bles which had a high correlation with the degree of tool wear were automatically identified by the system.Then the method of Mahalano-bis distance was used to analyze and calculate the eigenvectors,and the thresholds could be determined in different states of the tool.Ac-cording to the the calculation results,the wear state of the tool could be recognized.Finally,based on the above principles,a complete in-telligent monitoring system for tool wear of CNC machine tool was developed by using QT development platform.The test results show that the system can accurately monitor the wear state of the tool in real time.
关键词
刀具磨损/特征提取/状态监测/多传感器融合Key words
tool wear/feature extraction/state monitoring/multisensor fusion引用本文复制引用
基金项目
工信部高质量发展项目(ZTZB-22-009-001)
科技部2021高档数控系统及伺服电机项目(TC210H03A)
出版年
2024
NETL
NSTL
万方数据