According to the collected fault information of a domestic NC machine tool, the subsystem is divided, and the reliability allocation method is improved according to the NC machine tool correlation model to allocate the target value. The membership degree set of influencing factors is established using the analytic hierarchy process （AHP), and the centrality influencing factors of fault-related data are determined using the DEMATEL decision laboratory analysis method. The membership function set is determined by combining maintainability, maintenance time, failure downtime, failure times, and complexity. Then the reliability allocation factor of the NC machine tool is calculated. The impact factor is introduced into the ARINS allocation method to improve the method so that the improved method is suitable for the system with subsystems connected in series and fault correlation. Numerical examples show that the proposed method can reduce the failure time requirement of the subsystem compared with the traditional ARINS method. At the same time, to verify the rationality of the distribution results in this paper, the Monte Carlo simulation method is used to predict the reliability of the target machine tool based on the distribution results, and the calculation results prove the feasibility of this method. [ABSTRACT FROM AUTHOR]