汽轮机转子轮槽精铣刀磨损状态监测技术研究  

Study of Wear Condition Monitoring Technology of Turbine Rotor Wheel Slots Finishing Tool

作　　者：金健 胡小锋[1] JIN Jian;HU Xiao-feng(School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China)

机构地区：[1]上海交通大学机械与动力工程学院,上海200240

出　　处：《组合机床与自动化加工技术》2020年第5期90-94,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：上海市科委项目(19511105302)。

摘　　要：为实现汽轮机转子轮槽精刀磨损状态的在线监测,提出一种ARIMA与SVR相结合的刀具磨损量在线监测模型。构建基于ARIMA的信号特征预测模型,根据收集的历史信号数据预测刀具继续加工的信号特征;构建基于SVR的刀具磨损量监测模型,以信号特征为输入得到当前时刻精刀磨损量;将两个模型相结合,可以预测精刀加工下一条轮槽时的磨损量,对精刀下一时刻的状态做出准确判定。基于上述模型,可以为企业换刀时机的选择提供技术支持,最终提高加工质量与加工效率,实现最大经济效益。To realize the online monitoring of the wear conditions of the finishing tool used for processing turbine rotor wheel slots,an online monitoring model of tool wear in combination of ARIMA and SVR is proposed.An ARIMA-based signal feature prediction model is constructed,with which the signal characteristics of the tools can be predicted based on the collected historical signal data.A tool wear monitoring model based on SVR is constructed,which takes the signal characteristics as input to obtain the tool wear at the current time.Combining two models,it is possible to predict the amount of tool wear when the finishing tool is used to machine the next wheel slot,and to make an accuracy judgement of tool’s state at the next moment.Based on the model proposed,it can provide technical support for the changing time of the tool to the enterprise,and finally improve the processing quality and processing efficiency to achieve the maximum economic benefits.

关 键 词：刀具磨损 在线监测 ARIMA SVR 刀具磨损量预测 

分 类 号：TH16[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]