Reducing equipment failure rates is one of the key problems to be solved with the deployment of digital technology at industrial companies. This problem is relevant for rolling mills that define the production power of metal plants. This requires technical condition monitoring systems for the mechanical and electrical components of these devices. Currently, these systems shall be created by deploying digital twins in the automatic parameter control mode to assess the technical condition of the asset in question. Regular control on spindle connection wear is an important problem for the electromechanical systems of the rolling mill. The solution to this problem can be used for the reverse stands of plate mills. This is because the main electric drives of the upper and lower rollers (UMD and LMD) in these stands operate in the shock-loading mode. This results in spindle connection wear, spindle and roller failures, and equipment emergency downtime. This article presents the results of research aimed at improving the previously developed digital angular play monitor in spindle connections. The authors suggest using a digital twin based on Simulink Real Time software with Hardware-in-the-loop simulation (HIL). The virtual model of the electromechanical system is developed using Simscape domains and Matlab Simulink modules that help expand the capabilities of the model and its versatility. The hardware and software HIL simulation helps control virtual processes using the signals from the stand’s programmable logic controller (PLC). This improves the precision of indirect angular play measurement (recovery). The authors compare the oscillograms obtained from the virtual model and the mill. High play recovery precision has been confirmed. The results have been generalized to confirm the efficiency of the developed DT combined with HIL simulation.