Springback is always a technical problem in sheet metal forming. In this article, the rapid springback compensation control of two-dimensional hull plate is realized by theoretical calculation and numerical simulation. For the cylindrical shell, according to the bending forming theory of medium and thick plates, the total elastic-plastic bending moment is established, and the curvature change before and after springback is deduced. The curvature correction coefficient is determined by the precise numerical simulation technology. At the same time, the validity of the method is verified by cold bending experiment. For the shell with variable curvature, it is divided into several cylindrical surfaces according to the curvature gradient of its geometric section line. The compensation curvature array is obtained by the correction compensation algorithm of springback curvature of cylindrical plate, and the algorithm is verified by numerical simulation. The results show that the method is very close to the expected results. Thus, the efficiency and precision of forming will be improved, and the foundation of digitization of sheet metal forming is established.

Centrifugal pumps are susceptible to various faults, particularly under challenging conditions such as high pressure. Swift and accurate fault diagnosis is crucial for enhancing the reliability and safety of mechanical equipment. However, monitoring data under fault conditions in centrifugal pumps are limited. This study employed an experimental approach to gather original monitoring data (vibration signal data) across various fault types. We introduce a multi–scale sensing Convolutional Neural Network (MS–1D–CNN) model for diagnosing faults in centrifugal pumps. The network structure is further optimized by examining the impact of various hyperparameters on its performance. Subsequently, the model’s efficacy in diagnosing centrifugal pump faults has been comprehensively validated using experimental data. The results demonstrate that, under both single and multiple operating conditions, the model not only reduces reliance on manual intervention but also improves the accuracy of fault diagnosis.

In this study, a comprehensive digital twin monitoring system for ship equipment was designed and implemented, including the system architecture, key technologies, and applications. Through data-driven models and operational monitoring system analysis, our PSO-SVM-based time series prediction method demonstrated excellent predictive capabilities for catamaran equipment, achieving efficient fault warnings using a threshold method. The digital twin model and virtual scenarios constructed here provide a visualisation and simulation platform for equipment status monitoring, enhanced fault diagnosis and support for maintenance decisions. The system integrates real-time monitoring, fault warning, and data analysis, and testing results show good stability and accuracy. In addition, the system optimises the user experience through multi-round feedback testing, and ensures data security and privacy protection through multi-layer encryption, identity verification, and role-based access control. A case study indicates that the proposed system effectively monitors equipment status and provides fault warnings, and has broad application prospects and practical value. Future work will focus on optimising the functionality and improving the applicability and security of the system.