Remaining useful life (RUL) is a crucial indictor to measure the performance degradation of machine tools. It directly affects the accuracy of maintenance decision-making, thus affecting operational reliability of machine tools. Currently, most RUL prediction methods are for the parts. However, due to the interaction among the parts, even RUL of all the parts cannot reflect the real RUL of the whole machine. Therefore, an RUL prediction method for the whole machine is needed. To predict RUL of the whole machine, this paper proposes an RUL prediction method with dynamic prediction objects based on meta-action theory. Firstly, machine tools are decomposed into the meta-action unit chains (MUCs) to obtain suitable prediction objects. Secondly, the machining precision unqualified rate (MPUR) control chart is used to conduct an out of control early warning for machine tools’ performance. At last, the Markov model is introduced to determine the prediction objects in next prediction and the Wiener degradation model is established to predict RUL of machine tools. According to the practical application, feasibility and effectiveness of the method is proved.

剩余使用寿命（RUL）是衡量机床性能下降的关键指标。它直接影响维修决策的准确性，从而影响机床的运行可靠性。当前，大多数RUL预测方法都用于零件。但是，由于部件之间的相互作用，即使所有部件的RUL也无法反映整个机器的真实RUL。因此，需要用于整个机器的RUL预测方法。为了预测整机的RUL，本文提出了一种基于元动作理论的具有动态预测对象的RUL预测方法。首先，将机床分解为元动作单元链（MUC），以获得合适的预测对象。其次，加工精度不合格率（MPUR）控制图用于对机床性能进行失控预警。最后，引入马尔可夫模型来确定下一次预测的预测对象，建立维纳退化模型来预测机床的RUL。根据实际应用，证明了该方法的可行性和有效性。