An ensemble deep transfer learning method for fault diagnosis based on soft voting is proposed for diagnosing waterjet pump faults under variable working conditions. The source domain and few target domain data samples are normalized after FFT transformation and then fed into three deep transfer learning diagnosis models for training: the CORAL based deep transfer metric learning model, the MMD based deep transfer metric learning model, and the transfer component-based deep belief network. The target domain test samples are diagnosed and analyzed based on this approach. An ensemble deep transfer diagnosis model is subsequently established by combing the soft voting method to obtain the final diagnosis results. Through the diagnosis of three different types of faults in waterjet pumps under variable working conditions, the results show that the proposed ensemble deep transfer diagnosis model not only effectively addresses the high-precision fault diagnosis of waterjet pumps under variable working conditions, but also has better diagnostic accuracy than the single deep transfer fault diagnosis model.

The cylindrical floating production storage and offloading unit (FPSO) is a new type of offshore engineering equipment, which has been gradually applied to the development of the global offshore oil and gas resource. The motion response characteristics of a cylindrical FPSO suitable for the development of deepwater oil and gas fields in the South China Sea has been studied based on the three-dimensional potential flow theory and the Morison equation. The wet surface model and the hydrodynamic calculation model of the cylindrical FPSO are established by SESAM software to calculate the frequency domain motion response characteristics of the cylindrical FPSO in waves. The pitch, roll and heave motion responses of the cylindrical FPSO are compared with those of the ship-shaped FPSO with similar deadweight. The results show that the motion characteristics of the cylindrical FPSO are better than those of the ship-shaped FPSO. The heave motion responses of the cylindrical FPSO are also investigated for the cylindrical FPSO with different hull diameters, bilge box diameters, hull drafts and return periods of environmental conditions. The results can provide references for the overall design of the cylindrical FPSO.

The current study focuses on the project of a leveling dredger for gravel foundation laying of the submerged immersed tunnel. The real-time monitoring of the gravel foundation laying process for the submerged immersed tunnel has been performed by using technologies such as programmable logic controller (PLC), QT and database. The closed-loop control of the process of floating and sinking of the immersed tunnel is carried out by the PLC control using the proportion, integral and differential (PID) algorithm. The real-time monitor of the process of floating and sinking of the immersed tunnel is then implemented by the design of the computer interface of the real-time monitoring system, in order to achieve the technical requirements of the high precision and the high efficiency for the gravel foundation laying of the immersed tunnel. This mode of operation is original in China.