Optimization of a mooring system applying a deep neural network under multi-directional environmental conditions

Evaluation of natural computation techniques in the modelling and optimization of a sequential injection flow system for colorimetric iron(III) determination

The mooring system safety and the floating structure motion response in the survival condition are the main criteria in mooring system design. The safety factor of mooring system should be examined in the situation that the mooring system is intact and one mooring chain is broken. However, the previous researches mainly focus on the safety of the intact mooring system or the safety of the damaged mooring system in the steady stage. In this context, the safety of the damaged mooring system in the transient stage is investigated on a VLFS’s mooring system comprising 20 mooring lines. It is found that the effect of the breakage of the mooring chain in the transient stage is equivalent to an impact load, which will significantly reduce the safety factor of the mooring system while increasing the motion response of the VLFS. The optimal mooring system deployment in line breakage condition is further investigated by establishing a multi-objective optimization problem using NSGA-II. It can be found from the numerical results that the proposed optimal mooring system deployment technique can effectively improve the safety of mooring system while suppress motion response of the VLFS.

The evaluation of existing mooring system and the development of an appropriate optimization design became the key issues in the Liuhua 11–1 FPS dry-dock updating project because this optimized mooring system has to face new challenges, such as the update of site metocean conditions, the revision of wind force coefficients due to upgraded topsides, and the additional corrosion allowance for chain links due to extra 15-year service life extension compared with the original system design. A design team was formed to give the evaluation of the existing mooring system based on mooring line tensions and offset limits according to the latest industry standard for a permanent mooring system. Since the existing mooring system marginally failed the design requirements based on the evaluation, system optimization design focused on the adjustment of mooring line pretensions has been carried out to improve the mooring system performance and eventually to satisfy the classification requirements for the tension safety factors and the platform offset limits driven by the riser designs. The mooring system analysis was conducted in time domain. The Ariane program developed by BV was used in the detailed mooring system analyses. For the calibration and verification purpose, the system evaluation and the optimization design had also been independently verified with DNV's DeepC program. Introduction The LH 11–1 oil field is located about 200km southeast of Hong Kong in the South China Sea in approximately 310m depth of water. LH 11–1 FPS, which named ‘Nanhai TiaoZhan’, is a major component of LH 11–1 oil field development. The FPS was a modified drilling semi-submersible converted from a Sedco 700 series drilling rig built in 1975 and in 1995, it was converted again to a floating production unit in Singapore and then deployed at LH 11–1 oil field, permanently moored by 11 mooring legs. The Unit is classed by American Bureau of Shipping (ABS). It was originally designed for a service life of 10 years (from 1995) and has been continuously operating for more than 15 years. At the same time, a new oil field Liuhua 4–1 (OTC-24042), about 11 km away northwest LH 11–1, was in development planning with the utilization of LH 11–1 FPS facilities through a subsea tieback. Therefore, additional topsides capacities and the life extension of this aged semi-submersible FPS became necessary. CNOOC Ltd, Shenzhen is the owner of this LH 11–1 FPS. COOEC was selected as the contractor for the engineering and construction support of this FPS dry-docking upgrading and life extension project. CSSC Guanzhou Huangpu Shipbuilding Co., Ltd was contracted by the owner as the dry-docking shipyard for the upgrading construction.

The paper offers a design of an optical non-orthogonal multiple access (O-NOMA) system with Rayleigh fading channels by analysing the bit error rate (BER) and power spectral density (PSD) using machine learning (ML)-based and traditional signal detection methods. The primary focus is on various QAM modulation orders, such as 32-QAM, 64-QAM, 256-QAM, and 512-QAM. The research compares the performance of different detectors including deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), and conventional techniques. Among these, the DNN always yields better BER performance up to 10−5 BER at SNR values 12 dB lower than conventional techniques. For 32-QAM, in particular, the DNN provides a gain of 10.3 dB compared to conventional techniques, while similar gains are realized for higher QAM orders. PSD analysis also shows that the DNN is compact in terms of its spectral footprint, achieving out-of-band emissions as low as −690 dB, essential for reducing interference and maximizing spectral efficiency. Such results highlight the promise of using ML-based detection – particularly DNN – as an efficient and effective method for future, high-capacity optical NOMA systems functioning over a wide range of modulation schemes.

The purpose of this paper is to describe the authors' recent experience with the analysis, design, and installation of polyester rope mooring systems for deep water applications. Among the latest research activities, this article describes a series of full-scale tests performed on polyester rope provided for several spread moored systems offshore Brazil and West Africa. One of the main purposes of the performed tests was to determine non-linear stiffness characteristics of the rope; but other parameters used in the design and optimization of the polyester rope mooring system were also investigated. Introduction The past decade has seen a steady increase in the number of polyester rope deep-water mooring system for oil and gas exploration, especially floating production facilities. Brazil has always been in the frontier of the application of synthetic mooring ropes. Industry forecasts point to a strong increase in the number of such systems, considering the latest deepwater discoveries made offshore Brazil. Due to the past and present history of success in the use of polyester rope for the mooring of deep water floating system offshore Brazil, it is a general consensus that this trend will continue into the future and expand to other producing regions such as The Gulf of Mexico and West Africa as it can already be observed. There are many obvious advantages in using polyester ropes on deep water mooring systems. We could mention a few of them such as: lighter weight, desirable elastic characteristics and superb fatigue performance; on the other hand when engineering and installing such a system there are specific issues to be appropriately dealt with by the designer and the installation personnel. This paper will discuss some of the peculiarities associated to the design; analysis and deployment of polyester rope mooring system for deep water applications. The main topic of discussion in this article is a practical way to model the elastic stiffness of polyester mooring ropes in order to have a simple and reliable model that produces reasonably conservative extreme mooring loads and vessel-offsets. Such numeric model describing the elastic behavior of the polyester ropes have a significant impact on mooring system for floating facilities for deep water applications, with a specific application to the mooring of FPSO's. Typical Polyester Rope Mooring System for Deep Water FPSO Applications Fig. 1 depicts a typical deep water FPSO spread moor system. Each anchor leg is constituted by two segments of chain, one located at the bottom and the second close to the surface; joined by a single or multiple segments of polyester rope. In case of the mooring system shown on Fig. 1 we can see three (3) segments of polyester rope joined by two (2) short segments of chain.

This brief presents an integrated trajectory planning and attitude control framework for six-degree-of-freedom (6-DOF) hypersonic vehicle (HV) reentry flight. The proposed framework utilizes a bilevel structure incorporating desensitized trajectory optimization and deep neural network (DNN)-based control. In the upper level, a trajectory data set containing optimal system control and state trajectories is generated, while in the lower level control system, DNNs are constructed and trained using the pregenerated trajectory ensemble in order to represent the functional relationship between the optimized system states and controls. These well-trained networks are then used to produce optimal feedback actions online. A detailed simulation analysis was performed to validate the real-time applicability and the optimality of the designed bilevel framework. Moreover, a comparative analysis was also carried out between the proposed DNN-driven controller and other optimization-based techniques existing in related works. Our results verify the reliability of using the proposed bilevel design for the control of HV reentry flight in real time.

With the continuous progress of science and technology, the mechanical field is also constantly upgrading from traditional mechanical engineering to the mechatronics engineering and artificial intelligence (AI) is one of them. AI deals with a computer program that possesses own decision-making capability to solve a problem of interest with imitates the intelligent behavior of expertise which finally turns into higher productivity with better quality output. From the inception, various developments have been done on AI system which nowadays widely implemented in the mechanical and/or manufacturing industries with broaden area of application such as pattern recognition, automation, computer vision, virtual reality, diagnosis, image processing, nonlinear control, robotics, automated reasoning, data mining and process control systems. In this study, review attempt has been made for AI technologies used in various mechanical fields such as thermal, manufacturing, design, quality control and various connected fields of mechanical engineering. The study shows the blend mixed of AI technologies like deep convolutional neural network (DCNN), convolutional neural network (CNN), artificial neural network (ANN), fuzzy logic and many more to control the process parameters, process planning, machining, quality control and optimization in the mechanical era for smooth development of product or system. With the implementation of AI in mechanical engineering applications, the error, rejection of components can be minimized or eliminated and system optimization can be achieved effectively turn in economical better quality products.

Mooring designs are a critical concern for the offshore renewable industry. The common design processes for mooring systems involve multiple, lengthy cycles of simulation and experimentation to achieve suitable designs. In this paper, we propose, for the first time, a computationally efficient and physically transparent data-driven design optimisation approach using real measurements from only an initial estimated specification of the physical mooring system. This is applied to a complex renewable energy platform, the multiple float wave energy converter M4, by system identification with frequency response driven optimisation, computing the optimised design within an hour on a laptop. More specifically, although mooring force is highly nonlinear in relation to wave input, it is demonstrated by system identification that it is almost linear in relation to surge motion. Further, the low frequency force, separated from the linear wave frequency force by a wavelet filter, is modelled as a resonant mass spring damper. This approach thus effectively models the nonlinear mooring system using two linear models. Finally, the physical parameters, namely mass, damping ratio, and stiffness, are optimised and compared using parameter sweeping and convex optimisation methods to minimise fatigue loads. The results demonstrate that the proposed approach is cost-effective and computationally efficient for mooring system optimisation for complex floating systems. • A data-driven method for mooring design is introduced using system identification and frequency analysis. • Nonlinear mooring forces are modelled accurately using two linear models. • Demonstrating effectiveness on a complex platform - M4 wave energy converter. • It requires one initial design and yields interpretable, cost-effective results. • The optimisation completes within an hour on a standard laptop. • It halves fatigue estimates compared to initial designs.

This article primarily focuses on the design, testing, and validation of a deep neural network (DNN)-based control scheme for predicting multi-stage trajectory optimization in autonomous ground vehicles (AGVs) used in material transportation systems. The proposed design employs a multilayer structure. In the first layer, a desensitized trajectory optimization method is iteratively applied to establish a set of time-optimal multi-stage trajectories, taking into account noise-perturbed initial configurations. Subsequently, DNNs are trained using the preplanned optimal transportation trajectory dataset to learn the functional relationship between the system’s state and control actions in the second layer. To further enhance DNN performance, a simple yet effective data aggregation approach is designed and implemented. These trained DNNs are then utilized as motion controllers to generate real-time feedback actions. Numerical experiments are conducted to showcase the effectiveness and real-time applicability of the proposed control scheme in planning the multi-stage AGV transportation process.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

In this paper, a constraint Genetic Algorithm is used for the purpose of mooring pattern optimization. The Genetic Algorithm is applied through a mathematical formulation which is introduced to define a typical mooring system optimization problem. The mathematical formulation is used in a case study on a spread moored crane barge, operating in the vicinity of a jacket type platform, in order to minimize its surge motions towards the platform. For this purpose, a set of criteria regarding clearances between anchors and seabed preinstalled facilities (pipelines), and also between the crane barge and the jacket platform are presented and considered. An automatic process of repetitive analyses implementing a MATLAB code as an interface between the Genetic Algorithm and a mooring system analysis program is used, and an optimum solution is resulted by performing 4000 quasi-dynamic analyses in time domain. The effectiveness of the Genetic Algorithm in leading to an optimum mooring system pattern is studied and it is shown that using a proper formulation of the problem, the Genetic Algorithm can be a very useful tool for finding an optimum pattern for mooring systems in fields with constraints on anchor locations and vessel motions.

A methodology based on the coupling of experimental design and artificial neural networks (ANNs) is proposed in the optimization of a new flow injection system for the spectrophotometric determination of Al(III) with Arsenazo DBM, which has for the first time been used as chromogenic reagent in the quantitative analysis of aluminium. An orthogonal design is utilized to design the experimental protocol, in which three variables are varied simultaneously. Feedforward-type neural networks with faster back propagation (BP) algorithm are applied to model the system, and then optimization of the experimental conditions is carried out in the neural network with 3-7-1 structure, which have been confirmed to be able to provide the maximum performance. In contrast to traditional methods, the use of this methodology has advantages in terms of a reduction in analysis time and an improvement in the ability of optimization. The method has been applied to the determination of Al(III) in steel samples and provided satisfactory results.

Purpose This study aims to provide a detailed spatiotemporal analysis of indoor thermal comfort by introducing a novel approach for reconstructing air temperature and air velocity fields. Design/methodology/approach Strategic deep neural networks and refined computational fluid dynamics (CFD) were employed to reconstruct the air temperature and air velocity fields across five cases with varying window configurations and air diffusers. The predicted mean vote (PMV) and predicted percentage of dissatisfied (PPD) metrics, calculated based on the simulated air temperature and air velocity, were used to assess thermal sensation. Findings The refined CFD simulation approach could reveal a nonuniform distribution of air temperature, while the proposed deep neural networks enable precise and rapid reconstruction of the global temperature and air velocity distribution using only limited measurement data as input and eliminating the need for case-specific model fine-tuning. The spatiotemporal analysis of thermal comfort profiles reveals a nonuniform distribution of thermal comfort within the case office rooms, with cooler areas observed in the central middle of the space. This nonuniform thermal comfort profile may be influenced by design features such as window configurations and air diffusers, with a higher temperature observed near the window facades and the top ceiling. Research limitations/implications The proposed reconstruction methods are scalable to real-world empirical cases with various configurations, enabling accurate and efficient indoor environment modeling, which can further facilitate the design and optimization of real-time heating, ventilation and air conditioning control systems. The simulated spatiotemporal thermal comfort profile can serve as a valuable reference for building managers in climate regulation and space allocation, promoting a comprehensive approach to enhancing energy efficiency while maintaining thermal comfort. Originality/value This research presents a novel approach for reconstructing air temperature fields using deep neural networks, which require minimal data volume and are independent of boundary conditions, coupled with a refined CFD method that reveals the spatiotemporal patterns of air temperature and air velocity rather than relying on statistical mean estimations. Together, these techniques enable more detailed, dynamic and accurate analyses of thermal comfort.

Video hyperlinking represents a classical example of multimodal problems. Common approaches to such problems are early fusion of the initial modalities and crossmodal translation from one modality to the other. Recently, deep neural networks, especially deep autoencoders, have proven promising both for crossmodal translation and for early fusion via multimodal embedding. A particular architecture, bidirectional symmetrical deep neural networks, have been proven to yield improved multimodal embeddings over classical autoencoders, while also being able to perform crossmodal translation. In this work, we focus firstly at evaluating good single-modal continuous representations both for textual and for visual information. Word2Vec and paragraph vectors are evaluated for representing collections of words, such as parts of automatic transcripts and multiple visual concepts, while different deep convolutional neural networks are evaluated for directly embedding visual information, avoiding the creation of visual concepts. Secondly, we evaluate methods for multimodal fusion and crossmodal translation, with different single-modal pairs, in the task of video hyperlinking. Bidirectional (symmetrical) deep neural networks were shown to successfully tackle downsides of multimodal autoencoders and yield a superior multimodal representation. In this work, we extensively tests them in different settings, with different single-modal representations, within the context of video-hyperlinking. Our novel bidirectional symmetrical deep neural networks are compared to classical autoencoders and are shown to yield significantly improved multimodal embeddings that significantly (alpha=0.0001) outperform multimodal embeddings obtained by deep autoencoders with an absolute improvement in precision at 10 of 14.1% when embedding visual concepts and automatic transcripts and an absolute improvement of 4.3% when embedding automatic transcripts with features obtained with very deep convolutional neural networks, yielding 80% of precision at 10.

Photovoltaic power generation prediction is crucial for the effective integration of renewable energy into the grid, real-time grid balancing, and the optimization of energy storage systems. However, PV power generation is highly dependent on environmental factors such as weather conditions. Photovoltaic power generation prediction is crucial for the effective integration of renewable energy into the grid, real-time grid balancing, and the optimization of energy storage systems. However, PV power generation is highly dependent on environmental factors such as weather conditions. Effectively integrating environmental information remains a major challenge for photovoltaic power forecasting. This study proposes a hybrid deep learning model that incorporates an adaptive neural network to capture the latent relationships between PV power generation and environmental variables, thereby enhancing forecasting accuracy. The adaptive graph neural network employs a data-driven directed graph structure, where TCN and variable interaction layers are alternately stacked to better model the spatiotemporal coupling among variables for long-term PV output forecasting. The proposed model was evaluated on three sites located in different regions, with a fixed input length of 96 and output horizons ranging from 96 to 768 steps. Compared with state-of-the-art baselines, the model achieved average improvements of 2.19% and 1.57% in MSE and MAE at a 384-step horizon, and 2.81% and 2.47% at a 768-step horizon, respectively, demonstrating superior performance in long-term PV output forecasting tasks.