摘要
以刀具为研究载体,运用人工智能和智能优化等先进技术,成功实现了刀具磨损状态的智能预测。研究重点在于建立有效的刀具磨损状态预测方法,全面解析刀具磨损机理、形式及磨钝标准等关键信息。同时,构建了自采刀具磨损状态监测平台,以便收集并处理相关数据。在数据处理过程中,采用小波滤噪和EMD-Shannon能量熵进行特征筛选,构建出特征空间数据集,为后续构建预测模型提供坚实的数据基础。结合支持向量机分类算法和智能优化算法,构建出刀具磨损状态的智能预测框架。此框架不仅提高了预测精度,也为维护人员提供了强有力的工具,利于更好地进行刀具磨损状态的预测和维护工作。为增强实际应用价值,将所取得的成果整合至基于MATLAB GUI的刀具磨损状态智能监测原型系统,以图形界面方式呈现预测结果,使用户直观地了解和掌握刀具的磨损状态。结果表明,该方法具有高精度,刀具磨损状态的识别精度可达84%,为相关领域提供了可靠的技术支持。
The intelligent prediction of tool wear state is successfully realized by taking the tool as the research carrier and applying advanced technologies such as artificial intelligence and intelligent optimization.The research focuses on the establishment of an effective tool wear state prediction method,which comprehensively analyzes key information such as tool wear mechanism,form and dullness standard.At the same time,a self-mining tool wear state monitoring platform is constructed to collect and process relevant data.In the data processing process,wavelet filtering and EMD-Shannon energy entropy are used for feature screening,and a feature space dataset is constructed to provide a solid data foundation for the subsequent construction of the prediction model.The support vector machine classification algorithm and intelligent optimization algorithm are combined to construct an intelligent prediction framework for tool wear state.This framework not only improves the prediction accuracy,but also provides a powerful tool for maintenance personnel,which facilitates better tool wear state prediction and maintenance work.In order to enhance the practical application value,the obtained results are integrated into the MATLAB GUI-based tool wear state intelligent monitoring prototype system,and the prediction results are presented in a graphical interface,so that the user can intuitively understand and master the tool wear state.The results show that the method has high accuracy,and the recognition accuracy of tool wear state can reach 84%,which provides reliable technical support for related fields.
作者
梁璐娜
魏建安
袁雅阁
吴国阳
徐军
Liang Luna;Wei Jian’an;Yuan Yage;Wu Guoyang;Xu Jun(School of Mechanical Engineering,Guizhou University,Guiyang 550025,China)
出处
《机电工程技术》
2024年第2期29-34,123,共7页
Mechanical & Electrical Engineering Technology
基金
贵州省科技支撑计划(黔科合支撑[2023]一般433)
贵州大学自然科学专项(特岗)科研基金项目(贵大特岗合字(2022)40号)。
关键词
刀具磨损
智能监测系统
特征选择
智能优化算法
支持向量机
tool wear
intelligent monitoring system
feature selection
intelligent optimization algorithm
support vector machine
