Prediction of the spatial configuration of the umbilical cable during deep-sea mining in-situ tests is of great significance because dynamic change may cause the umbilical cable to touch the ground or overturn the mining vehicle. In the present paper, a real-time prediction method for the dynamic spatial configuration of the umbilical cable during the deep-sea mining process is proposed. At first, the environmental information, position and motion of the vessel–umbilical cable–mining system were collected by sensors arranged at different locations. Then, the data were converted and transformed to the local vessel coordinate system. After that, the commercial software OrcaFlex was employed to conduct real-time simulation, in which the spatial configuration of the umbilical cable was predicted by the lumped mass method. Furthermore, the proposed real-time simulation method was employed in a sea trial test of deep-sea mining in an area with a water depth of 1100 m. Comparing the prediction results with the trajectory of the USBL beacon obtained from the monitoring data, the maximum distance of some specific points was close to 5 m, and most of them were less than 3 m. Meanwhile, it could also give the dynamic responses of the deep-sea mining system. For example, the maximum top tension of the umbilical cable was less than 15 kN, which could be used to evaluate the health condition of the system. During the sea trial test, the proposed method played an important role in ensuring the safety of the umbilical cable during wide-range movement of the mining vehicle. With characteristics of good real-time performance, accurate prediction, high reliability and stability, the proposed method could enhance the confidence of engineers for on-site operation as a powerful digital tool for visualization of the subsea working state.

The umbilical cable is an important component of the deep-sea mining system, serving as the sole connection between the surface support vessel and the seabed mining system. The harsh marine environment poses significant challenges to umbilical cable safety. Methods based on traditional time-domain simulation are time-consuming and it is hard for them to meet the needs of real-time prediction. In this paper, a novel forecasting method is proposed, PFLM-PSML, which integrates the theory of potential flow (PF), the lumped mass method (LM), and a parameterised supervised machine learning method (PSML) to forecast the safety of umbilical cables. Six environmental and system parameters—wave height, wave direction, current velocity, current direction, cable length, and the relative position between vehicle and vessel—are used as model inputs, while outputs include cable top tension, curvature, and mining vehicle overturning moments. The model employs Latin hypercube sampling and an active learning approach with hybrid kernel functions to efficiently map input–output relationships. Validation through numerical simulations and a 6000 m deep-sea trial confirms that the proposed method achieves high accuracy and a computational speed thousands of times faster than traditional approaches, enabling real-time mechanical state prediction. Parametric analyses reveal that increases in wave height, current velocity, and water depth lead to higher cable tension and vehicle overturning moments. The PFLM-PSML framework demonstrates strong potential for real-time safety assessment and control of deep-sea mining systems under complex ocean conditions.