A repairable system approach of reliability assessment for multi-NC machine tools with time truncation based on stochastic point process is proposed,and a non-homogeneous Poisson process(NHPP) model for failure time is built.The point and confidence interval(CI) estimators of model parameters and reliability indices,such as accumulated mean-time-between-failure(MTBF) and failure intensity at truncated time,are all given by Fisher Information Matrix(FIM) method.The values of Akaike information criterion(AIC) show that repairable system approach has advantage over statistical distribution method when failure times of NC machine tools with minimal repair have monotonic trend in reliability analysis.The proposed model is passed by trend testing,renewal process testing and goodness-fit-test respectively.