In recent years, research has proposed several deep learning (DL) approaches to providing reliable remaining useful life (RUL) predictions in Prognostics and Health Management (PHM) applications. Although supervised DL techniques, such as Convolutional Neural Network Long-Short Term Memory, have outperformed traditional prognosis algorithms, they are still dependent on large labeled training datasets. With respect real-life PHM applications, high-quality data might be both challenging...

The maritime industry widely expects to have autonomous and semiautonomous ships (autoships) in the near future. In order operate maintain complex integrated systems a safe, efficient, cost-beneficial manner, autoships will require intelligent Prognostics Health Management (PHM) systems. Deep learning (DL) is potential area for this development, as it rapidly finding applications variety of domains, including self-driving cars, smartphones, vision systems, more recently PHM applications....

While automatic controllers are frequently used during transit operations and low-speed maneuvering of ships, ship operators typically perform docking maneuvers. This task is more or less challenging depending on factors, such as local environment disturbances, the number nearby vessels, speed it docks. article proposes a tool for onboard support that offers position predictions based an integration supervised machine learning (ML) model into dynamic model. The ML applied compensator...

Maintenance routines on ships today follow either a reactive maintenance (RM) or preventive (PvM) approach. RM can be regarded as post-failure repair, which might create large costs. PvM uses predetermined intervals, often involves unnecessary maintenance. Recently, prognostics and health management (PHM) has emerged potential way to develop an ideal policy. PHM aims provide optimal schedule through the use of sensor measurement for fault detection prognostics, among is first fundamental...

The deployment of floating offshore wind farms marks a pivotal step in unlocking the vast potential energy and propelling world towards sustainable solutions. Despite compelling prospects technology, its implementation is challenging. Complex installation procedures, associated high costs, evolving regulations can hinder widespread adoption. However, these challenges present opportunities for innovation cost reduction. This paper delves into technical, operational, economic aspects farm...

There are large numbers of high-rise buildings with glass curtain walls that require constant cleaning and is carried out using permanent gondola systems. This a laborious dangerous work in midair. Due to lack uniform building structure, wall maintenance becoming one the most appropriate fields for robotization. The development walking climbing offers novel alternative solution glass-wall cleaning. Application type robotic system can free workers from this hazardous realize an automatic...

This paper provides a brief survey of recent developments on the use electroencephalogram (EEG) sensors for detecting mental fatigue (MF) in human operators during tasks involving human-machine interaction. research topic has received much attention since there is consensus among experts increasing relation between failure and accidents safety-critical tasks. MF one most influential aspects leading to reliable way assess it using operator's physiological data, especially EEG. In past few...

The sea-state estimation is a fundamental problem in the development of autonomous ships. Traditional methods such as wave buoy, satellites, and radars are limited by locations, clouds, costs, respectively. Model-based prone to incorrect estimations due their high dependence on mathematical models As previous data-driven studies for consider only height use motion data from dynamic positioning (DP) vessels, this article introduces new, deep neural network (SSENET) estimate sea state light...

Wind farms are usually located in high-latitude areas, which bring a high risk of icing. Traditional methods anti-blade-icing limited by extra costs and potential damages to the original mechanical structure. Model-based heavily dependent on mathematical models blade icing, prone produce erroneous estimation. As data-driven better able achieve competitive performances for icing estimation, this article proposes temporal attention-based convolutional neural network (TACNN). This novel model...

Maintenance is the key to ensuring safe and efficient operation of marine vessels. Currently, reactive maintenance preventive are two main approaches used onboard. These either cost-intensive or labor-intensive. Recently, Prognostics Health Management has emerged as an optimal way manage operations. In such a system, fault prognostics aims predict remaining useful life based on sensor measurements. this paper, feasibility applying data-driven diesel engines investigated. Real-world...

High-fidelity models capable of accurately predicting ship motion are critical for promoting innovation and efficiency in the maritime industry. However, creating an advanced model that comprehensively represents system its interaction with dynamic environments has always been challenging. Many provide partial knowledge about a system. To handle deficiency improve fidelity, this artile, we propose hybrid modeling methodology, which prior describing effects is incorporated into data-driven...

Digitalization has become a key aspect of making maritime industries more innovative, efficient, and fit for future operations. One the most attractive aspects is concept <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">digital twins</i> , which refers to digital replicas physical assets, processes, systems that can be used as advanced tools design, operation, maintenance. This article introduces development twin research vessel (RV)...

The safety of maritime operations has become a paramount concern with the advancement intelligent ships. Ship stability and are directly impacted by roll motion, making prediction short-term ship motion pivotal for assisting navigators in timely adjustments averting hazardous conditions. However, predicting poses challenges due to nonlinear dynamics. This study aims predict leveraging encoder–decoder structure Bidirectional Long Short-Term Memory Networks (Bi-LSTM) teacher forcing. model is...

Purpose This paper presents the design of climbing robots for glass‐wall cleaning. Design/methodology/approach A systemic analysis basic functions a cleaning system is given based on research working targets. Then constraints designing robot are discussed. The driving method, attachment principle, mechanical structure and unique aspects three pneumatic named Sky Cleaners follow. In end summary main special features given. All tested site. Findings Our groups spent several years in developing...

We present an odometry‐free three‐dimensional (3D) point cloud registration strategy for outdoor environments based on area attributed planar patches. The approach is split into three steps. first step to segment each segments, utilizing a cached‐octree region growing algorithm, which does not require the 2.5D image‐like structure of organized clouds. second calculate small local faces inspired by idea surface integrals. third find correspondences between overlapping clouds using search and...

JOpenShowVar is a Java open-source cross-platform communication interface to Kuka industrial robots. This novel allows for read-write use of the controlled manipulator variables and data structures. JOpenShowVar, which compatible with all robots that KUKA Robot Controller version 4 (KR C4) 2 C2), runs as client on remote computer connected controller via TCP/IP. Even though only soft real-time applications can be implemented, opens up variety possible applications, making various input...

This paper presents a data-driven model for time series prediction of ship motion. Prediction based on past data is powerful function in modern support systems. For large amount sensor data, neural network (NN) considered as proper tool modelling the system. Efforts are made to compact NN structure through sensitivity analysis, which importance each input output quantified and lower ranked inputs eliminated. Further analysis about impact three different learning strategies, i.e. offline,...

To build a compact data-driven ship motion model for offshore operations that require high control safety, it is necessary to select the most influential parameters and analyze uncertainty of input parameters. This paper proposes framework sensitivity analysis data. The consists four components: data cleaning, surrogate model, analysis, results visualization. Data cleaning focuses on removal noise, transformation easy analysis. An artificial neural network (ANN) based constructed basis...

One objective of smart cities is to produce decisions that will address sustainability and climate change through big data citizen engagement. However, achieve this, local governments must two barriers engagement: concerns about privacy the difficulty poses nonexperts. Big by its nature produces a wide range varying insights; however, it difficult for nonexperts understand situations these insights describe, much less determine, communicate priorities solutions.

The advent of the COVID-19 pandemic disrupted global commercial activities and tourism industry heavily. Impacts on maritime transportation were huge, as seaborne trade represents over 80% merchandise trade. Investigating how has affected ship behaviours is significant for economic condition evaluation, port management. This paper develops an analysis method to mine knowledge from raw Automation Identification System (AIS) data. First, berths are identified by improved density-based spatial...

The concept of a modular climbing caterpillar robot is inspired by the kinematics real caterpillars. Two typical models and gaits are investigated based on crawling motion inchworm tobacco hornworm. Due to fixed constraints between suckers wall, gait engages changing kinematic chain which from an open closed chain, then in order. During periods, unsymmetrical phase method (UPM) used ensure reliable attachment passive wall. In closed-chain state, four-link model adopted fulfill constraints....

The ability of a robot vision system to capture informative images is greatly affected by the condition lighting in scene. This paper reveals importance active control for robotic manipulation and proposes novel strategies good visual interpretation objects workspace. Good illumination means that it helps get with large signal-to-noise ratio, wide range linearity, high image contrast, true color rendering object's natural properties. It should also avoid occurrences highlight extreme...