Equipment faults and machine failures can pose financial challenges for manufacturing organizations. To reduce or eliminate unexpected costs, it is essential to anticipate and address these failures. The utilization of Digital Twin (DT) technology is gaining momentum as a means to simulate system behaviour in the real world and identify unforeseen errors. This study aims to detect faults in Computer Numerical Control (CNC) machines, which are commonly used in manufacturing environments, using a DT approach. Regarding the methodology, the initial step involved data pre-processing processes. Subsequently, a DT model was developed and validated using real-time data. Machine learning techniques, specifically Artificial Neural Networks (ANN) and Support Vector Machines (SVM), were employed within the scope of the DT to detect step losses. In the second phase of the study, control charts were constructed using Statistical Quality Control (SQC) methods to characterize the faults. The algorithms used were assessed in terms of model generation speed and detection performance. The primary contribution of this study is the development of an executable DT capable of adapting to various CNC machines and robots.