In this paper, a method is proposed to accurately measure the torsional vibration of a ship’s propulsion shafting, and calculate its instantaneous torque based on instantaneous speed data. The instantaneous speed signal of a ship is measured by a data acquisition instrument indirectly under the deceleration condition, and then filtered by the five-point smoothing algorithm. The filtered instantaneous speed signal is further processed to calculate the maximum amplitude of the torsional vibration, along with the maximum torque of the propulsion shafting under specific operating conditions. The proposed method can effectively improve the calculation accuracy of the torsional vibration of the shafting, and provides reliable theoretical basis for setting the safe speed of the ship’s diesel engine.

Damage localization in GFRP (glass-fiber-reinforced polymer) composite plates is a crucial research area in marine engineering. This study introduces a feedback-based damage index (DI) combined with multi-label classification to enhance the accuracy of damage localization and address scenarios involving multiple damages. The research begins with the creation of a modal database for yachts’ GFRP composite plates using finite element modeling (FEM). A method for deriving a feedback-weighted matrix, based on the accuracy of the DI, is then developed. Sensitivity analysis reveals that the feedback DI is 50% more sensitive than the traditional DI, reducing false positives and missed detections. The associated feedback-weighted matrix depends solely on the structural shape, ensuring its transferability. To address the challenge for localizing multiple damages, a multi-label classification approach is proposed. The synergy between the feedback optimization and multi-label classification enables the rapid and precise localization of multiple damages in GFRP composite plates. Modal testing on damaged GFRP plates confirms the enhanced accuracy for combining the feedback DI with multi-label classification for pinpointing damage locations. Compared with traditional methods, this feedback DI method improves sensitivity, while multi-label classification effectively handles multiple damage scenarios, enhancing the overall efficiency of the damage diagnosis. The effectiveness of the proposed methods is validated through experimentation, offering robust theoretical support for composite plate damage diagnostics.