Segregation of the ferrous burden during blast furnace (BF) charging can cause uneven layer formation at the furnace throat, reducing bed permeability and disrupting gas–solid interaction. This study applies a discrete element method (DEM) model to the industrial-scale BF charging system (from the skip car to top hopper discharge) to examine segregation under real operating conditions. The model includes the full ferrous mixture (pellets, sinter, lump ore, and nut coke) and the real-scale geometries. A reference case representing current practice is analysed in detail and compared with systematically varied case studies. The results show that segregation generally decreases from the skip car to the top hopper due to partial remixing, but strong segregation is still observed. Lump ore and nut coke exhibit the strongest segregation, while pellets remain the least segregated. The order of pellets and sinter in the weighing bunkers strongly influences their segregation patterns, whereas variations in the sinter particle size distribution (PSD) and particle shape have only limited effects. The insights from this study provide a basis for developing practical strategies to mitigate segregation in industrial BF charging.

In blast furnace ironmaking, a mixture of iron ore pellets and sinter is charged in layers at the furnace top, with particle velocities reaching up to ∼10 m/s at the stock surface. The inherent differences in particle size, shape, and density between pellets and sinter pose challenges for maintaining a uniform mixture during this high-velocity charging, leading to segregation and uneven material distribution. This non-uniformity can negatively affect furnace efficiency and stability. Understanding segregation during charging is therefore crucial for optimizing the ironmaking process. The Discrete Element Method (DEM) can offer valuable insights, provided that the model parameters are calibrated and verified. This study presents a calibrated DEM model for a pellet–sinter mixture with a 50–50 mass ratio of both components. A novel high-velocity laboratory setup was used to simultaneously measure five different key performance indicators (KPIs) related to flow and packing behavior at various discharge heights, corresponding to different flow velocities. Calibration was performed at the highest flow velocity, representative of actual blast furnace conditions. The process involved creating response surface models for each KPI and using a multi-objective optimization approach with a desirability function to determine the model parameters. A step-wise calibration strategy was employed, first optimizing pellet and sinter interaction parameters individually, followed by calibration of the pellet–sinter interaction parameters. This approach proved effective, as the calibrated model accurately reproduced experimental data. Results also suggest that the calibration outcome is flow-invariant in this setup, with the model successfully predicting flow and packing behavior at lower discharge heights.

Reliable remaining useful life (RUL) prediction of rolling bearings serves as the core support for the prognostics and health management (PHM) of industrial rotating equipment. Although data-driven methods have achieved remarkable breakthroughs in prediction accuracy, the existing approaches still encounter three critical limitations: the insufficient informational dimensions of individual features, the poor adaptability between degraded features and prediction tasks in mainstream feature fusion models, and the channel-wise and temporal redundancy in multi-dimensional features that masks the inherent degradation trends of bearings. To tackle these challenges, this paper presents a novel rolling bearing RUL prediction method based on multivariate time series mixers with cross-channel convolutional fusion (CCF) (MTS-mixers-CCF). The proposed method initially constructs an initial feature set from bearing vibration signals. Subsequently, it establishes a feature-task adaptability evaluation framework using an adaptive differential evolution based on comprehensive evaluation metrics (CEM) algorithm to reconstruct a high-adaptability feature ensemble. Finally, it attains accurate RUL estimation through the MTS-mixers-CCF model, which reduces feature redundancy by means of factorization mechanisms and enhances inter-feature correlation via CCF layers. Experiments conducted on the widely adopted PHM2012 and XJTU-SY bearing datasets demonstrate that the MTS-mixers-CCF model outperforms traditional time series prediction methods and state of the art deep learning models, exhibiting significantly higher accuracy and stability for RUL prediction under ambiguous degradation trends. This research offers a robust and high-performance solution for rolling bearing RUL estimation, with promising application prospects in industrial PHM scenarios.

Existing studies on multi-vessel formations rarely combine physically based models of ship–ship hydrodynamic interaction with online formation control, so that energy benefits are typically assessed offline or only approximated through artificial potentials. This paper addresses this gap by embedding a reduced-order, hydrodynamics-aware resistance model into a hierarchical formation control framework for multi vessel systems. A three degree of freedom interaction model is incorporated into the cost function, enabling the supervisory controller to adaptively optimize inter ship spacing and formation geometry in a speed dependent and hydrodynamics aware manner. The lower level MPC ensures accurate trajectory tracking and stability under the guidance of the top level optimization. Four simulation studies are conducted to evaluate the proposed method. The platooning formation is first analyzed as a reference, followed by the triangular formation, which achieves balanced tracking performance and stability. The echelon formation is then examined, demonstrating significant energy savings in medium to high speed regimes while maintaining yaw stability. Finally, an unconstrained optimization scenario is explored, where the system autonomously adapts its geometry without prescribed patterns, revealing emergent energy efficient and stable arrangements across different speed ranges. Results show that the proposed approach not only reduces resistance and improves energy efficiency but also enhances formation adaptability and robustness under varying operating conditions. These findings provide new insights into hydrodynamics aware cooperative control and the development of energy conscious fleet management strategies for future maritime transportation.

The formation control of autonomous surface vessels presents significant challenges when operating in close proximity, where ship-to-ship interaction becomes non-negligible. While conventional formation control methods often neglect these interactions or simplify them excessively, this paper develops a centralized model predictive control (MPC) framework that explicitly incorporates a three-degrees-of-freedom interaction model. This interaction model is constructed empirically based on existing computational fluid dynamics results, offering an efficient and practical way to approximate proximity-induced forces in real-time. The proposed control strategy enables accurate trajectory tracking and effective disturbance adaptation in typical formation geometries, including platooning, parallel, and triangular formations. Simulation results demonstrate that the MPC controller can outperform traditional PID controllers in both tracking precision and interaction robustness across the configurations. Formation-specific performance differences are also analyzed in detail.

Inland shipping is a key component of transport infrastructure, as it provides an energy-efficient and cost-effective method for moving goods. This report aims to investigate how an autonomous mooring system for inland cargo vessels can be modeled and evaluated, to improve efficiency and safety during mooring operations. This study develops a vessel model that simulates relevant mooring behaviours under varying environmental conditions and designs a control system for accurate approach and successful mooring. Simulation results are analysed, focusing on approach accuracy and position-holding.

As the maritime industry moves toward fully autonomous operations, it is becoming increasingly important to assess the control performance and safety of Maritime Autonomous Surface Ships. This chapter presents a structured framework designed to facilitate testing and data collection using autonomous ship systems, thereby supporting the verification that autonomous operations align with International Maritime Organization standards. We discuss the integration of key hardware and software components for robust autonomous operation and evaluate these systems using analytical performance criteria in both simulated and real-world scenarios. The chapter concludes by proposing new key performance indicators necessary for the continued development of autonomous maritime systems. Through extensive datasets and collaborative research via Open Science-focused algorithms and designs, we aim to set the groundwork for future advancements in this field.

The stiffness model plays a crucial role in improving the performance of robots. During the operation of an underground mining cable-driven parallel robot (UMCDPR), insufficient stiffness can lead to motion instability, posing safety hazards. Additionally, the complexity of the underground mining environment, which is often accompanied by external disturbances, leads to offline stiffness indices failing when used underground as an optimal criterion. To address these problems, this article proposes a robust optimal stiffness direction (ROSD) index grounded in Rayleigh's theorem, which is characterized by three primary features: (1) strong robustness, (2) suitable for multi-trajectory optimization engineering problems, and (3) global visualization. Firstly, considering the influence of pulleys on the end-effector, the stiffness model of UMCDPR is modified. Secondly, a trajectory optimization method utilizing ROSD is introduced, incorporating the Kepler Conjecture and stiffness model correction. Finally, the characteristics of ROSD are validated through numerical simulations. Based on two numerical simulations, the ROSD index can serve as an optimal criterion for guiding stiffness optimization of UMCDPR. Furthermore, an optimal stiffness trajectory is obtained to meet the task objectives of UMCDPR.

Accurate prediction of mill load parameters is crucial to improving grinding efficiency and saving energy. Traditional prediction models have challenges such as poor interpretability, low prediction efficiency and differences in data distribution. This study innovatively proposed a multi-task prediction model that integrates physical information and domain adaptation. By constructing a physical-data-driven hybrid model, the physical relationship between mill load parameters is embedded into the model as prior knowledge to improve the prediction accuracy of the model. At the same time, multi-task learning is used to predict the material-to-ball volume ratio and the pulp density at the same time, which improves efficiency and reduces repetitive work. The domain adaptation method is introduced to ensure that the model maintains stable prediction performance when the data distribution changes. Laboratory ball mill data verification shows that the proposed model not only improves the prediction accuracy, but also adapts well to variable working conditions, showing significant superiority.

Multiagent reinforcement learning (RL) training is usually difficult and time-consuming due to mutual interference among agents. Safety concerns make an already difficult training process even harder. This study proposes a safe adaptive policy transfer RL approach for multiagent cooperative control. Specifically, a pioneer and follower off-policy policy transfer learning (PFOPT) method is presented to help follower agents acquire knowledge and experience from a single well-trained pioneer agent. Notably, the designed approach can transfer both the policy representation and sample experience provided by the pioneer policy in the off-policy learning. More importantly, the proposed method can adaptively adjust the learning weight of prior experience and exploration according to the Wasserstein distance between the policy probability distributions of the pioneer and the follower. Case studies show that the distributed agents trained by the proposed method can complete a collaborative task and acquire the maximum rewards while minimizing the violation of constraints. Moreover, the proposed method can also achieve satisfactory performance in terms of learning speed and success rate.

The inland waterway transport sector is facing increasingly stringent legislation to reduce emissions and improve energy efficiency. Speed planning has the potential to provide logistically compliant, energy-efficient, and emission-reducing voyages for inland vessels. However, current speed planning methods do not consider PM and NO_x emissions, nor do they consider alternative power systems to internal combustion engines (ICE) and full electric systems. These omissions have led to a lack of clarity on the impact of speed planning on the emission profile of inland vessels and the impact of alternative power systems on energy consumption. In this paper we propose a validated speed planning method that considers the emission profile (CO₂, PM₁₀, and NO_x) and different engine types for inland vessels in an leg-based speed planning approach while taking into account varying fairway water depth and speed. Through a use case we show that the vessel can achieve a 7.26% energy, 5.37% CO₂ and fuel, 3.85% NO_x, and 6.77% PM₁₀ reduction while maintaining the same arrival time; showing a distinct difference of this method compared to slow steaming. We also find that CO₂, NO_x, PM₁₀, and energy are not directly proportional when making speed adjustments. Finally, we analyze the adverse effects of emission control areas and emission limits on the energy consumption and arrival times of vessels with non-zero emissions propulsion.

Wet ball mill plays a key role in the grinding process, and its load state directly affects production efficiency, energy consumption and product quality. Aiming at the problems of poor interpretability of pure data-driven models and complex modeling of mechanism models under variable working conditions, a hybrid prediction model DAPINN combining deep learning and physical information is proposed. By introducing the deep hidden physics model principle and using the characteristics of neural networks to approximate arbitrary functions to simulate complex physical partial differential equations, the physical interpretability of the model is enhanced. At the same time, the model introduces domain adaptation technology to improve the prediction accuracy and generalization of the model under variable working conditions. Experiments were conducted on data collected from a small ball mill in the laboratory. The experimental results show that under variable working conditions, the prediction accuracy of the DAPINN model is better than that of the pure data-driven model.

Digital twins and visual monitoring of conveyor systems require accurate digital models of dynamic bulk material flows, but existing methods struggle to achieve both speed and precision. This study develops a rapid online method to reconstruct dynamic bulk material flows on conveyor belts. First, a standardized online reconstruction scheme using visual detection of material flow contour lines is presented. Then, a feature detection algorithm is proposed to extract more refined points from laser line skeleton to accelerate the reconstruction process. An iterative-filtering interpolation algorithm that generates smooth interframe point clouds is introduced to improve mesh quality. Experimental results demonstrate that our method outperforms traditional corner detection-based reconstruction techniques in feature point detection, accuracy, mesh quality, and runtime performance. This research provides a practical solution for material handling digitalization, promoting the advancement of conveyor system digital twins and potentially improving operational efficiency and predictive maintenance in bulk material handling industries.

This article presents an innovative visual method for measuring material mass online by quantified conveyor belt deformation with deep learning, which offers a noncontact and safe alternative to traditional pressure- and radioactivity-based weighing techniques. The correlation between the belt deformation and the carried material mass is further investigated through finite element simulations. Then, a visual weighing method by belt deformation is proposed, comprising a calibration algorithm to construct a measurement model using a gated recurrent unit-based network, and an online measurement algorithm to calculate material mass with the trained network. Finally, a case study is presented to analyze the effect of different dimension configurations and networks. The results validate that the proposed method attains a notable accuracy and is suitable for high-velocity conveyor environments. The demonstrated benefits signify an advancement in visual perception of materials, enabling a new approach for intelligent operation and monitoring in material handling field.

Calibration of discrete element method (DEM) models is crucial for the realistic simulation of granular materials. However, it remains a challenging task, especially for multi-component mixtures due to their higher complexity and larger number of parameters involved. This study presents a systematic and computationally efficient calibration framework designed to address these challenges, focusing on pellet-sinter mixtures, as a representative case of two-component mixtures commonly used in blast furnace steelmaking. The framework integrates sensitivity analysis, machine learning-based surrogate modelling with adaptive sampling, and genetic algorithm-driven optimisation techniques to minimise the number of required DEM simulations. Using this approach, we achieved a high-accuracy surrogate model (R² = 0.95) for seven DEM parameters with only 110 data points, highlighting the efficiency and robustness of the framework. These parameters were successfully calibrated with a relative error of less than 2 %. Moreover, the calibrated parameters for the base case (i.e., 50–50 pellet-sinter mass ratio) remained valid across different mass ratios and layering orders, eliminating the need for recalibration. Overall, the proposed framework offers a reliable, cost-effective, and adaptable solution for DEM calibration of two-component mixtures. Its flexibility and efficiency make it a promising tool for extending to more complex systems, facilitating the development of DEM models for a wide range of industrial applications involving granular mixtures.