In the context of promoting green and low-carbon energy development and structural transformation, traditional energy technology urgently requires innovation and enhanced capabilities. Therefore, intelligent technology for marine engineering equipment is rapidly advancing but faces challenges such as weak independent innovation capabilities, lacking some critical core technologies, and insufficient supporting capacities for key components. To drive the intelligent development of marine engineering equipment and accelerate the construction of intelligent marine engineering equipment, this paper reviews the practical innovations of key equipment in the development of marine oil and gas resources. This includes three research areas: Marine flexible risers and umbilical, marine floating structures, and monitoring technology for marine structures. Firstly, by systematically expounding the current development status of marine flexible riser and umbilical, intelligent algorithms in structural analysis and design are summarized. Secondly, the development progress of intelligent marine floating structures is introduced and the limitations of current analysis technology and future research directions are highlighted. Lastly, the application research of intelligent monitoring technology for marine equipment structures is reviewed and monitoring technology as a crucial pathway for intelligent perception is emphasized. With the rapid advancement of information technology, traditional automation methods are inadequate to address new challenges in the marine equipment maintenance process. The article suggests that comprehensive application of various intelligent technologies such as full perception, real-time interconnection, analysisbased decision-making, autonomous learning, dynamic prediction, and collaborative control in marine engineering equipment should be an inevitable trend for future development.

After many times of maintenance of an offshore platform it is found that there is crack propagation at the corner which connects the living building to the deck. The idea of crack length identification based on the multi-dimensional strain around the crack is proposed in this paper. A finite element model of offshore platform with initial crack is built. Multi-scale strain data and corresponding crack length are used as feature input and output for the machine learning model respectively. The crack length is predicted by gradient boosting regression tree (GBRT) model. Test results show that the value of MSE and R2 can reach 0.0006 and 0.9991, respectively. At the same time, the model is proved to have good anti-interference to noise.

This paper aims to analyze the free vibration response of functionally graded plates with complex cutouts. An isogeometric analysis method based on a novel quasi-three-dimensional higher-order shear deformation theory called the spectral displacement formulation (SDF) is employed to predict the free vibration characteristics of the plates. The SDF can deal with the three-dimensional elasticity solution and naturally avoid the shear-locking problem, making it suitable for plates with varying thicknesses. The governing equations for free vibration of the plates are derived using the D'Alembert principle and the principle of virtual work, and the equations are discretized using isogeometric method. The results of several numerical examples are compared with existing reference solutions. It is concluded that the proposed analysis method can accurately and effectively analyze the free vibration of functionally graded plates with complex cutouts.

For metal pipe with pretension and corrosion defects, local elastic-plastic deformation often occurs at the defects and affects the corrosion electric field characteristics of the metal pipe. This paper takes 20^# steel metal pipe with ellipsoidal corrosion defect as the research object, and establishes a mechanical-electrochemical coupling model of elastic-plastic stressstrain and local electrochemical corrosion to study the effects of different tensile displacements on stress distribution and corrosion electric field characteristics of metal pipes. The results show that mises stress, corrosion potential, corrosion current density and corrosion electric field mode are symmetrically distributed with respect to the defect center under different tensile displacements, with the maximum value occurring at the defect center, and the values all increase with the increase of tensile displacement. The influence of plastic deformation stage on the local electrochemical characteristics of defects is significantly greater than that of elastic deformation stage. The corrosion at the defect is composed of a series of small galvanic cells, and the increase of tensile displacement can accelerate the corrosion rate at the defect.

This paper bases on the equivalent linearization method and pseudo excitation method to conduct random vibration analysis of cylindrical LNG isolation tanks under seismic excitation and investigates the influence of the liquid level and shape of the isolation tanks on the random seismic response. First, based on the acceleration response spectrum, a seismic power spectral density function is obtained according to the Kaul method, and a Haroun-Housner model of the LNG tank is established. Second, the equivalent stiffness and damping of the isolation system are obtained according to the equivalent linearization method, and the frequency domain equations of motion of the equivalent linear system are established, and a pseudo excitation method is developed to solve them iteratively. Finally, numerical examples are given, where the random responses of isolated storage tanks under different liquid levels and radii are calculated and the effects of tank radius and liquid level height on the response are studied, so as to provide certain reference for the optimization design of isolated storage tanks.

Due to the combination of vortex-induced vibration and coupled platform motion, fatigue damage is a potential issue for catenary flexible risers. This paper reports the experimental results of vortex-induced vibration of a catenary flexible riser hinged underneath a two-degree-of-freedom vortex-induced moving platform. The in-plane and out-of-plane responses of the riser are monitored by high-speed cameras while the cross-flow and in-line motions are recorded by laser displacement sensors. The strong and weak couplings between the platform motion and riser vibration are identified. Moreover, the strong coupling is further classified into two types: riser vibration dominated and platform motion dominated ones. The in-plane and out-of-plane responses of the riser also present the interaction which varies along the span. Affected by the in-line motion of the top platform, the interaction between in-plane and out-of-plane responses is weakened. Because of the spatial frequency competition, the number of required samples for machine learning varies along the riser. The maximum required number occurs in the middle part, followed by the top part as a result of the platform motion.

LNG cryogenic flexible hose is one of the key devices in exploitation, transportation and storage of LNG (liquefied natural gas), which is called as the "blood vessel" of LNG transportation system. With the exploitation and transportation of LNG gradually from offshore to deep sea in recent years, there is a broader development prospect for LNG cryogenic flexible hose and its application technology. In order to verify the design theory and safety of engineering application of LNG cryogenic flexible hose, experimental testing technology has become an indispensable analytical means to study the mechanical properties of the hose. This paper focuses on the research of experimental test of LNG cryogenic flexible hose and investigates related technologies. Then both domestic and abroad research progress of experimental testing technology of LNG cryogenic flexible hose is summarized and the future research hotspots of experimental testing technology are prospected. Since China started related research of LNG cryogenic flexible hose relatively late it is of great significance to break through key technologies of LNG cryogenic flexible hose and to realize the domestic manufacturing process.

Flexible riser is a critical transportation device for offshore oil and gas development, and its innermost structure is the carcass layer, which is built from flat steel plates through multiple passes of roll bending and winding lock forming processes. Due to the complex structural characteristics and numerous geometric parameters of the carcass layer, as well as the longitudinal and transverse deformations of the steel plate during forming process, the influence of key processing parameters on its deformation characteristics during roll bending shaping is not clear. In this paper, based on dimensional analysis principles, dimensionless expressions for the relationship between key processing parameters and the deformation characteristics (bending angle) of the carcass layer in multi-pass roll bending are established. Using polynomial regression and symbolic regression methods, the expanded forms of dimensionless expressions are obtained to clarify the effects of processing parameters (elastic modulus, steel plate thickness, roller radius, roller spacing) on the bending angle of the carcass layer. Conclusion shows that the steel plate thickness has a significant impact on the bending angle and that when the thickness increases from 1 mm to 2 mm, the bending angle decreases by 27.74%.

A catenary single-point mooring requires a simulation environment based on inputs such as basic conditions, operating conditions, self-storage conditions, motion and force requirements, and multi-point testing to find the optimal design. The paper uses deep learning method to solve the mooring system prediction problem. Firstly, two datasets, i.e., self dataset and operation dataset are acquired by simulation calculation. Then the self dataset is predicted and the data is divided into three categories: local, global, and global plus local for training and validation, and a two-layer full-connected neural network is used to predict the regression problem with an accuracy of over 90%. As the results are not satisfactory when the model is applied to more complex operation datasets, a self-built model DBRNet12 complex network using DNN+BN+ReLU as the minimum component is added to handle more operation data, thus obtaining an average accuracy of 86%. The self-built RNet40 network based on the idea of residuals on DBRNet12 achieves a 90% average accuracy. In terms of network architecture, a deep neural network is built to predict parameters through fully connected layers, and the network structure is continuously optimized. Finally, the evaluation of relative error is used to evaluate the effectiveness of the prediction and the residual network is used for optimization. Through this procedure, the application effect of deep learning methods in mooring system prediction problems is achieved, and the ideas provide references for further research and practice in this field.

The LNG unloading arm is an important channel connecting the carrier and the LNG receiving station pipeline to transport liquefied natural gas, which is called the "throat" of the receiving station. In this paper, The finite element structure of the unloading arm is calculated and analyzed for the first time, and some design optimization suggestion is given. There is a large stress concentration at the joint of the three-dimensional joint and the pipe of the outer arm, the structural design process should be paid attention to. The structural strength of the lengthening position of the support box is weak, a pipe with thicker wall should be used. Aiming at the emergency release system of the key core components of the unloading arm, an innovative hoop locking mechanism is designed based on the principle of mechanical dead point, and finite element calculation and performance test results show that the stress and deformation of the hoop locking device meet the design requirements, and that its stability and reliability also meet the needs of the unloading arm operation, thus providing a reference for safe and reliable operation of large LNG unloading arm.

Cryogenic hoses are an essential part of floating LNG transfer systems and play a crucial role during the side-byside offloading process between FLNG units and LNG carriers. With the ongoing development of offshore oil and gas fields moving into deeper waters, LNG cryogenic hoses have a significant and irreplaceable application prospect. This paper conducts a theoretical analysis and establishes a computational fluid dynamics (CFD) numerical model for the fluid flow characteristics inside the corrugated tubes of cryogenic hoses. Using FLUENT, simulations of internal flow characteristics under various operating conditions and structural parameters are performed for cryogenic hoses. The results provide a series of trends in terms of internal flow pressure drops and heat transfer coefficients, derivating a theoretical model for the flow and heat transfer in cryogenic hoses. This model provides a theoretical basis and correction factors for more accurate and efficient calculations. The findings of this work support the design of cryogenic hoses and lay a foundation for industrial production and domestic application of these hoses.

Being oriented to a single platform carrying a single specific communication function business, the current marine communication network status monitoring and platform scheduling system is difficult to meet the increasingly complex development needs such as multiagent collaboration, multimeans integration, and multibusiness integration in marine communication networks. This article proposes an intelligent monitoring and scheduling system design scheme for maritime emergency communication networks. This scheme can meet the requirements of emergency scenarios in maritime emergency communication networks, and realize a multiagent collaborative scheduling system by analyzing real-time monitoring information from sky, air, shore, sea, and submarine agents. It is a highly adaptable intelligent monitoring and collaborative scheduling system featuring flexible network construction and rapid network supplementation for marine emergency communication networks. It can also solve the problem of real-time data transmission between heterogeneous communication systems by means of flexible combination of offshore platforms and communication loads, thus greatly improving the support capability of maritime communication networks. A demonstration system has been constructed based on the national major project "Smart Ocean" emergency communication experimental network and applied to real-time information perception, emergency response planning, event handling, video consultation and other business in typical marine emergency application scenarios. It has been validated that the intelligent monitoring and scheduling system described in the article can meet the intelligent development of marine communication networks.