Enhancing maritime safety: developing an accessible real-time semantic wave imaging analyser for seakeeping

增强海上安全：开发一种易于使用的实时语义波成像分析仪，用于适航性

• 批准号: EP/X035778/1
• 负责人: Ya Huang
• 金额: $ 76.37万
• 依托单位: University of Portsmouth
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FX035778%2F1
• 关键词: Enhancing; maritime; safety; developing; accessible

Our proposed research aims to develop an ocean wave imaging analyser to predict wave- vessel-payload-crew interaction. This is a currently missing prerequisite for optimal seakeeping of fast vessels. Seakeeping, concerning the control of vessel motion when subjected to waves and the resulting effects on humans, systems, and mission capacity, remains one of the biggest challenges in maritime safety. Vessel operational practices (48%) and human factors (17%), both key to seakeeping, have been the main safety recommendations amongst 1212 investigations, conducted by the European Maritime Safety Agency in the past decade.Before making any control decisions, mitigating detrimental effects on seakeeping requires accurate and real-time modelling of the approaching waves in the perimeter of the vessel. The predicted wave loading is essential for any precise estimation of vessel motion, but it is absent. To derive such a model, 3D wave geometry evolving in real time - a dynamic 4D scene - is required. However, the computational time required for existing sensing and modelling approaches are too long for the decision windows of any vessel operations. This process presently takes more than tens of seconds in order to anticipate and react at close proximity. This leads to three specific challenges we propose to tackle.1) Develop a real-time stereo wave imaging system for fast vessels to create an imaging database in order to reconstruct accurate 4D wave scenes.2) Reduce inference time of extracting wave dynamic features, e.g. wave propagation speed, direction, magnitude by comparing and adapting different deep learning methods.3) Predict dynamic loading on the vessel, payload and crew from reconstructed 4D wave.Storms are expected to become more common and severe due to climate change. The maritime industries, including fishing, marine science, defence, offshore energy, and search and rescue services, will need to adapt. A shock mitigation strategy is essential for all crafts that undertake rough water transits manned or unmanned. In heavy seas, 'wave slams' induce high-acceleration events exposing occupants to mechanical shocks and whole-body vibration of extreme magnitudes with severe chronic and acute consequences on human health. The UK regulation based on the Control of Vibration Work Regulations 2005 and the Merchant Shipping and Fishing Vessel Regulations 2007, with daily limits for shock and vibration exposure. Similar legislation applies throughout Europe and other countries. It is not always practicable for fast vessel operators to carry out necessary activities and duties while complying with these limits. In many situations, crew shock and vibration exposures are the limiting factor of the operational capability.It is practical to provide crew with shock mitigating seating. Seats or cabs, however, protect the crew, but not the hull, hull-mounted equipment or payload. If the coxswain continues to drive to the same discomfort level, the loading on the vessel will be increased with the potential of immediate and long-term damages. This is a current area of concern in the whole industry. An experienced coxswain can maintain a high speed while mitigating the impact severity via constant adjustment of the helm and throttle. This skillset requires understanding of many factors: the characteristics of the oncoming wave and the likely response of the vessel and crew.The development of an 'intelligent' imaging system capable of reading the dynamic oncoming sea, sensing craft motion, and its effects on crew and cargo will be essential to the seakeeping and maritime safety.Our industrial-driven research will address this challenge through extensive onboard stereo imaging experimentation, state-of-the-art numerical modelling and development of new artificial intelligence framework. The outcomes will transform critical operational safety of merchant shipping, fishing, defence, offshore energy assets, rescue services.

我们提出的研究旨在开发一种海浪成像分析仪，以预测波浪-船只-有效载荷-船员的相互作用。这是目前缺少的快速船舶最佳耐波性的先决条件。耐波性是指船舶在波浪作用下的运动控制以及由此对人员、系统和使命能力的影响，仍然是海上安全面临的最大挑战之一。船舶操作实践（48%）和人为因素（17%）都是耐波性的关键，是欧洲海事安全局在过去十年进行的1212调查中的主要安全建议。在做出任何控制决策之前，减轻对耐波性的不利影响需要对船舶周边的逼近波浪进行准确且实时的建模。预测的波浪载荷对于船舶运动的任何精确估计都是必不可少的，但它是缺失的。为了导出这样的模型，需要在真实的时间中演化的3D波浪几何形状-动态4D场景。然而，现有传感和建模方法所需的计算时间对于任何船舶操作的决策窗口来说都太长了。目前，这个过程需要数十秒以上的时间才能进行预测并在近距离做出反应。这导致了我们提出要解决的三个具体挑战。1）为快速船舶开发实时立体波浪成像系统，以创建成像数据库，从而重建准确的4D波浪场景。2）通过比较和适应不同的深度学习方法，减少提取波浪动态特征的推理时间，例如波浪传播速度，方向，幅度。3）预测船舶上的动态载荷，有效载荷和船员从重建的4D波。风暴预计将变得更加普遍和严重，由于气候变化。包括渔业、海洋科学、国防、近海能源和搜救服务在内的海洋产业将需要适应。对于所有载人或无人进行波涛汹涌的水上运输的船只来说，减震策略至关重要。在波涛汹涌的海面上，“波浪冲击”引起高加速度事件，使乘员遭受机械冲击和极端幅度的全身振动，对人类健康造成严重的慢性和急性后果。英国法规基于2005年《振动工作控制条例》和2007年《商船和渔船条例》，规定了冲击和振动暴露的每日限值。类似的立法适用于整个欧洲和其他国家。快速船经营人在遵守这些限制的情况下进行所需的活动和职责并不总是切实可行的。在许多情况下，机组人员的冲击和振动暴露是限制操作能力的因素，为机组人员提供减震座椅是可行的。然而，座椅或驾驶室保护船员，而不是船体、船体安装设备或有效载荷。如果舵手继续驾驶到相同的不适水平，则船上的负载将增加，并可能造成立即和长期的损害。这是目前整个行业关注的一个领域。一个有经验的舵手可以保持高速，同时通过不断调整舵和油门来减轻冲击的严重程度。这一技能需要了解许多因素：迎面而来的波浪的特征以及船只和船员可能的反应。开发一种“智能”成像系统，能够阅读迎面而来的动态海浪，感知船只运动，其对船员和货物的影响将对耐波性和海上安全至关重要。我们的工业-驱动研究将通过广泛的机载立体成像实验、最先进的数字建模和开发新的人工智能框架来应对这一挑战。这些成果将改变商船、渔业、国防、海上能源资产和救援服务的关键运营安全。