基于时间序列的数控设备状态智能评判方法

针对因异构数控系统多样造成设备数据采集和状态评判困难的问题,设计一种通用的数据采集和设备状态智能评判方法. 首先由能耗信号采集器采集设备加工时的能耗信息并分析能耗特征. 采用加工仿真或预先采集的方法,收集各NC代码加工时设备主轴的能耗信息,进行信号变换形成标准能耗信息库. 然后检测数控设备的能耗信息并视为时间序列,应用时间序列的相关理论和方法对信号进行变换,采用基于编辑距离的相似性度量方法,将该时序信息和标准信息库中的信息进行比对,识别判断数控设备的加工工件类别和状态,并进行统计分析. 在此基础上,设计开发了数控设备状态智能采集系统,实现了设备数据的采集. 最后,通过实例验证该方法的可行性与可靠性. 

Time Series Analysis Based Intelligent Evaluation of NC Machine Tools Working Status

It is difficult to collect data and evaluate the status of NC machine tools automatically because of the diversity of isomeric CNC systems. Aiming at this problem, a general method is designed. First, an energy consumption data collector is designed to collect energy consumption data of NC machine tools' spindle and the data feature is analyzed. Then the standard energy consumption data by NC machining simulation or pre-acquisition during the operation of every NC code program is collected and further a standard energy consumption database is built according to the standard data. Second, to judge the type of work piece and the status of NC machine tools, the time series theory is used to deal with the energy consumption data by compared with the data that of the standard database. Finally, the feasibility and reliability of the proposed method is verified through an example.