Motion Prediction Research Articles

Predicting heave and pitch motions of an FPSO using meta-learning

Real-time motion prediction is helpful in guaranteeing the operation stability of a Floating Production Storage Offloading (FPSO) unit. Recurrent neural networks (RNNs) are becoming feasible alternatives to numerical simulations for motion prediction as artificial intelligence develops rapidly. In this study, model-agnostic meta-learning (MAML) is combined with RNNs to deterministically predict the heave and pitch motions of a ship-shaped FPSO. This approach is motivated by the fact that MAML improves training efficiency without losing accuracy. The data came from a scaled model test conducted at Shanghai Jiao Tong University’s deepwater wave basin. Before introducing MAML, we verified that long short-term memory (LSTM) and gated recurrent unit (GRU) could accurately predict the heave and pitch of about 7.68 s into the future. With fewer learnable parameters than LSTM, GRU demonstrates slightly better accuracy. Therefore, this study focuses particularly on the combination of GRU and MAML. The parameters of MAML, including order of derivative, step size, number of adaption gradient updates, and batch size of the tasks, are evaluated systemically in terms of accuracy and training efficiency. With the assistance of MAML, GRU’s training efficiency for heave and pitch has significantly improved, increasing by approximately 65% and 55%, respectively. Meanwhile, the prediction error for both has decreased by about 10%. Notably, MAML’s performance is minimally affected by variations in incoming wave direction and sea state, as well as the randomness and temporal variability of the motion. MAML is a powerful tool that enables RNNs to achieve real-time prediction of FPSO motion.

Impact of seismotectonic source zoning and seismic parameter: Sensitivity study on probabilistic seismic hazard assessment

The demarcation of seismic area source zones plays a pivotal role in probabilistic seismic hazard assessment (PSHA). In this study, we developed five distinct seismotectonic area source models, integrating large and small areas based on geological, tectonic, and seismological data. Logic tree methodology is utilized in FRISK88M for PSHA. Analysis revealed higher hazards in models with larger area sources compared to those with smaller ones. Hazard deaggregation of seismotectonic model-5 (SM5) is examined and sensitivity analysis of various logic tree nodes is investigated in terms of percent deviation w.r.t mean hazard at various spectral and return periods. The findings underscore that recurrence methods fall into "insensitive level" (≤5%), source mechanism and a-value distribution belong to "low sensitive level" (>5–15%), magnitude distribution lies in "medium sensitive level" (>15–25%), b-value distribution belongs to "high sensitive level" (>25–35%), and ground motion prediction equations (GMPEs) and depth distribution falls into "very high sensitive level" (>35%) in relation to seismic hazard.

Dynamic nonparametric modeling of sail-assisted ship maneuvering motion based on GWO-KELM

Accurately predicting the state of ship motion is crucial for ship navigation control with energy efficiency optimization studies. When modeling the motion of novel ships equipped with propulsion devices such as sails, it is essential to consider the effects of sail thrust and lateral forces on the ship's motion states. Building upon the analysis of sail force and sail-assisted ship motion modeling, this paper proposes a ship motion dynamic modeling method utilizing Kernel Extreme Learning Machine (KELM) regression. By optimizing the hyperparameters of the kernel function using the Grey Wolf Optimizer (GWO) algorithm and incorporating a sliding time window for dynamic model updating, the proposed approach combines the efficient learning mechanism of KELM with the global search capability of GWO, effectively enhancing prediction accuracy and timeliness. Utilizing KVLCC2 ship model motion data, simulation data from the sail-assisted ship “New Aden” and real ship data as case studies, comparative analysis with traditional models such as SVM and ELM. The results demonstrate that the GWO-KELM modeling approach exhibits robustness and high prediction accuracy, the MAE of the proposed model in the real ship motion prediction effect is reduced by 8.89% and the RMSE is reduced by 9.44% compared with the other models, which significantly enhance the predictive performance of sail-assisted ship maneuvering motion states.

AI-Driven Model Prediction of Motions and Mooring Loads of a Spar Floating Wind Turbine in Waves and Wind

AI-Driven Model Prediction of Motions and Mooring Loads of a Spar Floating Wind Turbine in Waves and Wind

Multi-granularity spatial temporal graph convolution network with consecutive attention for human motion prediction

Human motion prediction is attracting increasing attention for its numerous potential applications in fields including autonomous driving, video surveillance and virtual reality. However, accurate motion prediction is challenging due to the complex spatial dependencies, dynamic temporal correlations and high dimension of human pose sequences. Existing graph-based methods rarely consider positional and channel information of the feature map, resulting in lower prediction accuracy. Therefore, we propose a novel multi-granularity spatial temporal graph convolution network with consecutive attention (MSTCA) for human motion prediction. Firstly, a multi-granularity spatial convolution network is introduced to capture spatial joint features through multiple kernel sizes. Then, consecutive attention module is proposed to capture both positional and channel information of the feature map. Next, MSTCA uses multi-granularity temporal convolutional network to extract temporal correlations with multiple receptive fields and predict future poses. Finally, a decoder composed of a 2D convolution layer and several PRelu layers integrates the output of the whole model. Experimental results on the GTA-IM and PROX datasets demonstrate that our method significantly improves the accuracy of human motion prediction in comparison to the existing approaches.

Advancing polar motion prediction with derivative information

Abstract Earth Orientation Parameters (EOP) are essential for monitoring Earth’s rotational irregularities, impacting satellite navigation, space exploration, and climate forecasting. This study introduces a hybrid prediction model combining least-squares (LS) and vector autoregression (VAR) to improve Earth’s Pole Coordinates (x, y) forecast accuracy. Using daily sampled IERS EOP 20 C04 data from 2013 to 2023, we conducted 1,000 yearly random trials, performing 48 forecasts per year. Our method evaluates six data combinations, including primary variables (x, y) and their derivatives ( x ̇ , y ̇ $\dot{x},\dot{y}$ ). Results show a systematic improvement in prediction accuracy, especially for ultra-short-term forecasts (10 days into future), with derivative information stabilizing the solutions. The best-performing combination ( x , y , x ̇ , y ̇ $x,y,\dot{x},\dot{y}$ ) achieved a mean absolute prediction error (MAPE) reduction (with respect to the reference data combination – x, y) of up to 8 % for the y and 7 % for the x over a whole 30-day forecast horizon. These findings highlight the effectiveness of incorporating derivatives of polar motion time series into prediction procedure.

Model experimental studies on active heave compensation control strategy for electric-driven offshore cranes

Ship-mounted heave compensation offshore cranes are indispensable for isolating connected payloads from the support vessel during lifting operations under harsh sea conditions. In this paper, an innovative adaptive robust control strategy is presented for the electric-driven active heave compensation (EDAHC) system, combining an equivalent model predictive control (EMPC) method with a bias proportional integral derivative (BPID) framework to effectively mitigate the adverse effects of wave-induced heave motions from the support vessel on the suspended payload. Building upon the inherent field-oriented control in the permanent magnet synchronous motor (PMSM), the BPID-based control structure is introduced, motivated by its prompt responsiveness and robust resistance against model discrepancies and irregular disturbances. Facilitated by a torque compensation mechanism, the EMPC-based control scheme, synthesized with an autoregressive integrated moving average (ARIMA)-based heave motion prediction algorithm, is subsequently developed to achieve nonlinear friction deadzone correction and adaptive regulation of BPID parameters, thereby ensuring optimal performance of the EDAHC system within specified state and input constraints. Comparative experimental tests conducted on a scaled EDAHC testbed validate the superior capabilities of the proposal in station-keeping, position tracking, constraint satisfaction, and robustness against parametric uncertainties.

Neural network algorithms of a curved riga sensor in a ternary hybrid nanofluid with chemical reaction and Arrhenius kinetics

To improve the thermal management systems in industrial operations, there is a need for the prediction and complexity of advanced fluid motion across various physical conditions on different geometries. Further, ternary nanofluid flow across curved Riga surfaces plays a significant role in thermal management systems, chemical industries, thermal management systems, biomedical, environmental engineering, and more. Based on the above importance the current study focuses artificial neural network (ANN) model on the ternary nanofluid flow over a curved Riga surface in the presence of chemical reaction and activation energy. Proper assumptions and boundary layer approximation were used to develop the model. Using appropriate similarity variables, the governing equations are further simplified to ordinary differential equations (ODEs). Runge Kutta Fehlberg's 4th-5th order and shooting process are applied to solve the simplified equations. The primary objective is to improve the construction and optimization of thermal administration systems and other manufacturing procedures by gaining a deeper knowledge of the fluid motion and characteristics of heat transfer involved. Graphs are used to provide additional context for the important dimensionless constraints. The obtained data was utilized to train the ANN model, which was then verified towards numerical values of important engineering coefficients. The results reveal that the addition of solid volume fraction will enhance the thermal profile while declining the concentration profile. The reaction rate parameter will decline the concentration, and a reverse trend is seen for the activation energy parameter. The constructed model exhibits an outstanding degree of precision throughout the procedure, spanning all phases of the research.

A new wake superposition model and its application in collision prevention control of tri-riser array system

In the field of offshore oil exploitation, the compact multi-riser arrangement increases the risk of collision and has an adverse impact on production and the marine environment. The solution to this problem involves accurate motion prediction and collision prevention control under the effect of flow field superposition between risers, but there is little research on this related theory. This paper improves the traditional wake shielding effect model and further proposes a wake shielding superposition effect model for the mutual influence between risers, in order to establish a comprehensive accurate motion control model for tri-riser array system. A solution method is introduced for this model, both vibration and collision analysis are conducted for the system. The study revealed that solely augmenting the spacing inadequately mitigates system collisions, and active control is an inevitable choice. Based on this, this paper further designs an active boundary controller that is easy to implement in engineering, to achieve collaborative collision prevention control for three risers, and verifies its stability. Compared with traditional PD control, the proposed control method exhibits significant superiority, which can effectively reduce vibration amplitude, significantly increase dynamic spacing, and thus effectively prevent collisions between risers.

Physically adjusted ground motion prediction equations for induced seismicity at Preston New Road, UK

Predicting ground motions due to induced seismicity is a challenging task owing to the scarcity of data and heterogeneity of the uppermost crust. Dealing with this requires a thorough understanding of the underlying physics and consideration of inter-site variability. The most common ground motion model used in practice is the parametric ground motion prediction equation (GMPE), of which hundreds exist in the literature. However, relatively few are developed with a focus on induced seismicity. Developing GMPEs that are specific to an appropriate magnitude-distance range (R<30\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R < 30$$\\end{document} km; 2≤M≤6\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2 \\le M \\le 6$$\\end{document}) is important for induced seismicity applications. This paper proposes a framework for the development of physically-based GMPEs to provide more accurate and reliable estimates of the potential induced-seismicity ground motion hazard, allowing for better risk assessment and management strategies. To demonstrate this approach, a new set of GMPEs for the 2018-2019 induced seismicity sequence at the Preston New Road (PNR) shale gas site near Blackpool, United Kingdom, is presented. The physically-based GMPE was developed based on a pseudo-finite-fault stochastic ground motion simulation, calibrated with parameters derived from the spectral analysis of weak-motion records from induced seismic events. An optimization-based calibration technique using the area metric (AM) was subsequently performed to calibrate optimal parameters for simulating ground motion at the PNR site. Finally, using a suite of forward simulations for events with 1≤M≤6\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1 \\le M \\le 6$$\\end{document} recorded at distances up to 30 km, combined with empirical data, a location-specific GMPE was derived through adjustment of an existing model.

Game-Theoretic Adversarial Interaction-Based Critical Scenario Generation for Autonomous Vehicles

Ensuring safety and efficiency in the rapidly advancing autonomous vehicle (AV) industry presents a significant engineering challenge. Comprehensive performance evaluations and critical scenario testing are essential for identifying situations that AVs cannot handle. Thus, generating critical scenarios is a key problem in AV testing system design. This paper proposes a game-theoretic adversarial interaction method to efficiently generate critical scenarios that challenge AV systems. Initial motion prediction for adversarial and surrounding vehicles is based on kinematic models and road constraints, establishing interaction action spaces to determine possible driving domains. A novel evaluation approach combines reachability sets with adversarial intensity to assess collision risks and adversarial strength for any state, used to solve behavior values for each interaction action state. Further, equilibrium action strategies for the vehicles are derived using Stackelberg game theory, yielding optimal actions considering adversarial interactions in the current traffic environment. Simulation results show that the adversarial scenarios generated by this method significantly increase incident rates by 158% to 1313% compared to natural driving scenarios, while ride comfort and driving efficiency decrease, and risk significantly increases. These findings provide critical insights for model improvement and demonstrate the proposed method’s suitability for assessing AV performance in dynamic traffic environments.

On the road to comfort: Evaluating the influence of motion predictability on motion sickness in automated vehicles

Automated vehicles could increase the risk of motion sickness because occupants are not involved in driving and do not watch the road. This paper aimed to investigate the influence of motion predictability on motion sickness in automated vehicles, as better motion anticipation is believed to mitigate motion sickness. In a simulator-based study, twenty participants experienced two driving conditions differing only in turn directions. The repetitive condition featured a repeating turn direction pattern. The non-repetitive condition contained pseudo-randomly ordered turn directions. To mimic an ‘eyes-off-the-road’ setting and prevent visual motion anticipation, road visuals were omitted. No significant differences in sickness or head motion, a metric for motion anticipation, were found between the conditions. No participant recognised the repeating turn pattern. This suggests no increased motion anticipation in the repetitive condition, possibly due to a reduced ability to recognise a repeating motion pattern in one degree of freedom within more complex motion.

Machine Learning Approaches for 3D Motion Synthesis and Musculoskeletal Dynamics Estimation: A Survey.

The inference of 3D motion and dynamics of the human musculoskeletal system has traditionally been solved using physics-based methods that exploit physical parameters to provide realistic simulations. Yet, such methods suffer from computational complexity and reduced stability, hindering their use in computer graphics applications that require real-time performance. With the recent explosion of data capture (mocap, video) machine learning (ML) has started to become popular as it is able to create surrogate models harnessing the huge amount of data stemming from various sources, minimizing computational time (instead of resource usage), and most importantly, approximate real-time solutions. The main purpose of this paper is to provide a review and classification of the most recent works regarding motion prediction, motion synthesis as well as musculoskeletal dynamics estimation problems using ML techniques, in order to offer sufficient insight into the state-of-the-art and draw new research directions. While the study of motion may appear distinct to musculoskeletal dynamics, these application domains provide jointly the link for more natural computer graphics character animation, since ML-based musculoskeletal dynamics estimation enables modeling of more long-term, temporally evolving, ergonomic effects, while offering automated and fast solutions. Overall, our review offers an in-depth presentation and classification of ML applications in human motion analysis, unlike previous survey articles focusing on specific aspects of motion prediction.

Development and use of semi-empirical spectral ground motion models for GPP-induced micro-earthquakes in Southern Germany

This study provides a comprehensive exploration of ground motions associated with micro-earthquakes induced by geothermal power plants (GPP) in Southern Germany and proposes corresponding ground motion prediction equations (GMPE). Initiating with a statistical analysis of recorded seismic data from the GPP in Insheim, the study is extended to the greater Munich area. For the latter, the scarce recorded data are merged with physics-based simulation data. The recorded data in Insheim, Poing, Unterhaching and the simulated data in Munich are compared to existing GMPEs for GPP-induced events, highlighting the need of new region-specific prediction equations. The proposed GMPEs are expressed in terms of peak quantities, spectral accelerations and velocities, separating the horizontal and vertical direction. The regression curves exhibit a good alignment with both recorded and simulated data, within an acceptable range. Notably, the results reveal higher spectral quantities at shorter periods (<0.1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$<0.1$$\\end{document} s), underscoring the importance of this characteristic in seismic assessment. The article shows an exemplary application for a low-rise residential building, located at a hypocentral distance of 3 km. While the building meets serviceability standards for an MW\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$M_W$$\\end{document} up to 2.5, the verification fails at MW=3\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$M_W=3$$\\end{document}, emphasizing the need for robust risk assessment. These findings contribute to the understanding of ground motions of GPP-induced events, offering practical implications for serviceability verifications and aiding informed decision-making in geothermal energy projects.Graphical abstract

A behavioral conditional diffusion probabilistic model for human motion modeling in multi-action mixed human-robot collaboration

Collision avoidance is priority for human-robot collaboration (HRC). Human motions have stochastic, making it difficult for robots to recognize humans. To establish accurate human motion models is important to recognize humans. In the collaboration process, the action categories may suddenly and continuously switch to adapt to complex production tasks, namely, the stochastic of human motions, and we call this collaboration process as multi-action mixed HRC. The previous HRC rarely considered the stochastic of human motions. However, the stochastic in multi-action mixed HRC brings great challenges to human motion modeling. On the one hand, the same observed motions may develop into different action categories, the motion distribution need to be predicted. On the other hand, the connected motions between two action categories are missing, and need to be predicted. To address these two problems, this study introduced diffusion probabilistic models to capture the stochastic of human motions. However, the current diffusion probabilistic models cannot realize the high-accuracy human motion prediction. Most of them did not consider the condition distribution in diffusion process, and did not comprehensively capture the spatiotemporal characteristics between human and robot. To solve the above problems, a behavioral conditional probabilistic diffusion model (BCDPM) is proposed. The BCDPM model can capture the stochastic of human motions to model the human motion distribution. A mask mechanism is combined with diffusion prior generated by BCDPM model to predict the missing connected motions. The BCDPM model consists of the designed constrain network, the denoising network, and enhanced memory graph neural network. The constrain network can generate the condition distribution, the denoising network and enhanced memory graph neural network can capture the short term and long term spatiotemporal characteristics, respectively. Moreover, the overlapping motion primitives are explicitly encoded into the implicit BCDPM model to mine commonalities of motions. The results show the proposed method can obtain excellent accuracy in prediction and outstanding F1 score in collision detection experiment.

Probabilistic Seismic Hazard Assessment of the Southwestern Region of Saudi Arabia

In relation to its rapid infrastructure expansion, exemplified by projects like the Najran Valley Dam or the rehabilitation of agricultural terraces, Saudi Arabia stands out among the Arabian Gulf nations. To mitigate the earthquake-related risks effectively, it is imperative to conduct an exhaustive analysis of its natural hazards. The southwesternmost region of Saudi Arabia is the main subject area of this study for the probabilistic seismic hazard assessment (PSHA), which aims to identify the peak ground acceleration (PGA) and spectral acceleration (SA) values. The investigation encompasses a 10% and 5% probability of occurrence over a 50-year exposure time for both B/C and C NEHRP soils. In order to take into account the earthquake activity that takes place in the vicinity of the Red Sea Rift, which in fact may have an impact on the seismic hazard in this active tectonic region, different seismic source zones were especially designed for this evaluation. Various characteristics such as the uncertainties related to the b-value, the expected maximum magnitude, and different ground motion prediction equations (GMPEs) were integrated using a logic tree scheme. Additionally, regression relationships between the computed ground motion values were established, and a novel design response spectrum was developed and recommended for several cities. Regarding the key findings, it is significant to highlight that the seismic hazard decreases towards the northeast, when moving away from the Red Sea Rift, confirming anticipated trends where proximity to the rift corresponds to increased seismic hazard. Notably, cities such as Farasan Island, Jazan, Al Qunfundhah, Al Lith and Al Birk present the highest observed hazard values among all the cities analyzed. For these cities, the obtained maximum SA values for both 475 and 975 years under B/C site conditions are as follows: 0.268 g and 0.412 g, 0.121 g and 0.167 g, 0.099 g and 0.150 g, 0.083 g and 0.135 g, and 0.066 g and 0.118 g, respectively. These results emphasize the crucial necessity of adequately evaluating and thoroughly updating the seismic hazard inherent to these particular areas to enhance the risk reduction and disaster readiness initiatives.

Tacking over-smoothing: Target-guide progressive dynamic graph learning for 3D skeleton-based human motion prediction

Graph Convolution Network-based (GCN-based) approaches show promising performance on 3D skeleton-based human motion prediction due to its natural graph representation and outstanding ability for spatial–temporal dependencies modeling for human motion. However, the existing GCN-based methods inherently have difficulties in designing deep GCN-based structures for human motion prediction due to the over-smoothing issue. Although the over-smoothing issue has been studied in many scenarios, few attempts focus on this problem in 3D human motion prediction tasks. Therefore, we propose a novel deep GCN architecture termed TPDGN (Target-guide Progressive Dynamic Graph Network) to solve this issue in a motion prediction context. The core of the proposed TPDGN is the progressive dynamic graph leaning block, which is developed to model the dynamic graph pattern. We claim that the key to solving the over-smoothing issue is to reduce the loss of motion features and boost graph representations. Accordingly, we further explore the progressive learning mode by the specific target guidance for the motion prediction task, which aims at learning rich motion dependencies to tackle over-smoothing. Empirical results show that our approach could improve the over-smoothing issue, achieving state-of-the-art results on three public datasets. The codes is available at https://github.com/1111szu/TPDGN.

How Do Combustions Actuate High-Speed Soft Robots?

The combustion actuation method opens a unique pathway for high-performance soft robots, allowing for high accelerations in multifunctional applications. Along with multifunctionality come great challenges in effective robot structure design, accurate control and prediction of combustion-actuated motions, and practical implementation of various applications. However, research in this nascent field remains fragmented, lacking central guiding principles. To systematize these works, this review article summarizes state-of-the-art technologies in combustion-actuated soft robots, addressing three key questions: How to design a combustion-enabled soft robot? How to predict its movements and control it? and How to practically apply it.

Vertical line time domain green function and its applications in numerical simulation of ship seakeeping performance

In present study, a vertical line source time domain Green function is proposed and the subsequent numerical evaluation methods are described in detail. For which, Taylor expansion and Chebyshev approximation algorithms are originally extended from point source to line source for small parameters, as well as asymptotic expansions are extended for large parameters. Meanwhile, polynomials are originally proposed to replace the asymptotic expansions to improve the computational efficiency. The accuracy and stability of the proposed method are validated through several cases and good agreement can be obtained.Furthermore, a hybrid Green function method based on the vertical line source Green function and Rankine source is developed for time domain simulation of seakeeping performances of ships. With respect to the hybrid method, the flow domain is divided into inner part and outer part by an artificial control surface. The first-order Taylor Expansion Boundary Element Method (TEBEM) based on the Rankine panel distribution is applied in the inner part, while three-dimensional panel method based on the vertical line source Green function distribution is adopted in the outer part. Under this circumstance, motions of the single-ship (Slender Wigley and Blunt Wigley) and two-ship (two side-by-side ships) in head waves are numerically investigated. The numerical results agree well with the experimental data, which proved the feasibility and the accuracy of present hybrid Green function method for motion prediction of both single-ship and two-ship.

Node Adjustment Scheme of Underwater Wireless Sensor Networks Based on Motion Prediction Model

Node Adjustment Scheme of Underwater Wireless Sensor Networks Based on Motion Prediction Model