Search results

This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the limitations of expert demonstration data and reduces the dimensionality of the agent’s exploration space to speed up the training convergence rate.

Firstly, the decay weight function is set in the objective function of the agent’s training to combine both types of methods, and both RL and imitation learning (IL) are considered to guide the agent's behavior when updating the policy. Second, this study designs a coupling utilization method between the demonstration trajectory and the training experience, so that samples from both aspects can be combined during the agent’s learning process, and the utilization rate of the data and the agent’s learning speed can be improved.

The method is superior to other algorithms in terms of convergence speed and decision stability, avoiding training from scratch for reward values, and breaking through the restrictions brought by demonstration data.

The agent can adapt to dynamic scenes through exploration and trial-and-error mechanisms based on the experience of demonstrating trajectories. The demonstration data set used in IL and the experience samples obtained in the process of RL are coupled and used to improve the data utilization efficiency and the generalization ability of the agent.

Because of the various advantages of reinforcement learning (RL) mentioned above, this study uses RL to train unmanned aerial vehicles to perform two tasks: target search and cooperative obstacle avoidance.

This study draws inspiration from the recurrent state-space model and recurrent models (RPM) to propose a simpler yet highly effective model called the unmanned aerial vehicles prediction model (UAVPM). The main objective is to assist in training the UAV representation model with a recurrent neural network, using the soft actor-critic algorithm.

This study proposes a generalized actor-critic framework consisting of three modules: representation, policy and value. This architecture serves as the foundation for training UAVPM. This study proposes the UAVPM, which is designed to aid in training the recurrent representation using the transition model, reward recovery model and observation recovery model. Unlike traditional approaches reliant solely on reward signals, RPM incorporates temporal information. In addition, it allows the inclusion of extra knowledge or information from virtual training environments. This study designs UAV target search and UAV cooperative obstacle avoidance tasks. The algorithm outperforms baselines in these two environments.

It is important to note that UAVPM does not play a role in the inference phase. This means that the representation model and policy remain independent of UAVPM. Consequently, this study can introduce additional “cheating” information from virtual training environments to guide the UAV representation without concerns about its real-world existence. By leveraging historical information more effectively, this study enhances UAVs’ decision-making abilities, thus improving the performance of both tasks at hand.

The periodically fully developed laminar heat transfer and fluid flow of an array of non‐uniform plate length, aligned at angles to air flow direction, have been investigated by numerical analysis in the Reynolds number range from 15 to 410. To implement the periodic boundary condition in both streamwise and spanwise directions and to confine the computation exactly within one cycle, proposes a linear interpolation technique, which has been proved successful by comparing the results with those obtained in an extended domain. It has been found that with an increase in the ratio of the long plate length to that of the short plate and with a decrease in the ratio of the transverse pitch to the streamwise cycle length, both the Nusselt number and friction factor decrease. Comparison of the numerical results of Nusselt number and friction factor with relevant experimental results have been performed. The agreement should be judged reasonably good.

The purpose of the study is to investigate and reveal this relationship of various engineering demand parameters (EDPs) of this structural type and intensity measures (IMs) under intra-plate earthquakes.

The nonlinear finite element model used was calibrated first to the existing results of the shaking table test to verify the modeling technique.

This paper investigated the relationship between intensity measures and various engineering demand parameters of cable-stayed bridges using intra-plate earthquakes. The correlation analysis and Pearson coefficient are used to study the correlation between EDPs and IMs. The results showed that peak ground velocity (PGV)/peak ground acceleration, peak ground displacement and root-mean-square of displacement showed weak correlation with IMs. PGV, sustained maximum velocity, a peak value of spectral velocity, A95 parameter, Housner intensity and spectral acceleration at the fundamental period, the spectral velocity at the fundamental period and spectral displacement at the fundamental period were determined to be better predictors for various EDPs.

This paper investigated the correlation between the intensity measures of intra-plate earthquakes with the seismic responses of a typical long-span cable-stayed bridge in China. The nonlinear finite element model used was calibrated to the existing results of the shaking table test to verify the modeling technique. In total, 104 selected ground motions were applied to the calibrated model, and the responses of various components of the bridge were obtained. This study proposed PGV as the optimal IM.

While in common English-language parlance speaking of “online celebrities” encourages the conflation of new forms of famousness with existing discourses on mass media stardom and fandom, the Mandarin Chinese term wanghong, a shorthand term for wangluo hongren (literally “person popular on the internet”), frames the enticing shores of online celebrity through the peculiar lexical domain of a grassroots popularity. The figure of the wanghong has in recent years accompanied the development of social media platforms in China, becoming a profitable profession, an inspirational role model, a morally condemnable by-product of internet economies, and in general a widely debated social phenomenon among local users. Drawing on interviews with more and less successful local online celebrities and discussions with their audiences, this chapter offers an up-to-date portrayal of the various forms of wanghong currently vying for attention on Chinese social media platforms, illustrating how popularity is crafted along with narratives of professionalism and economic aspirations intimately connected to the sociotechnical contexts of contemporary China.

Purpose: Environmental, social, and governance (ESG) factors indeed play a vital role in sustainability efforts across various sectors and industries. ESG factors are often aligned with the United Nations’ Sustainable Development Goals (SDGs), which provide a framework for addressing global challenges related to poverty, inequality, climate change, environmental degradation, and more. Countries that prioritise ESG considerations in their operations and decision-making processes contribute to achieving the SDGs, thus advancing sustainability. The study explores the interplay between ESG practices and overall sustainability outcomes. This involves examining how ESG considerations influence environmental conservation, social equity, and economic resilience and how these factors collectively contribute to sustainability goals.

Methodology: Data envelopment analysis (DEA), which is performed in order to find out the most efficient countries, which will provide valuable insights into the complex relationship between ESG factors and sustainability, informing decision-making and driving positive change towards a more sustainable future.

Findings: ESG practices transform to sustainable development efficiently in half of the EU countries; however, the efficient countries differ depending on the model. Demonstrating the efficient transformation strengthens the country’s case for sustainability. Countries that embrace ESG practices not only contribute to environmental and social well-being but also enhance their competitiveness and long-term value-creation potential.

Implications: Policymakers can use the findings to advocate for policies and regulations that promote ESG integration and sustainable development. This may include measures to incentivise responsible business practices, enhance corporate transparency and disclosure, support sustainable finance initiatives, and strengthen regulatory frameworks to address emerging ESG risks.

Durability of concrete can be enhanced by reducing the pore size/volume of pores or by entrapping the pores. This can be achieved by adding concrete admixtures that have particle size finer than cement. In this study, GNP, having particle size much smaller than cement, has been introduced/added to concrete mix to control the pore size in concrete to tape out the contribution of GNP in the durability enhancement of concrete.

Different concrete mixes, at various water–cement ratios and amounts of graphene, have been manufactured to produce concrete containing three different %ages of GNP, i.e. 0%, 0.05% and 0.1%. To demonstrate the effect on durability of the concrete through the addition of GNP, these concrete samples have been subjected to repeated Freeze-Thaw cycles. Followed by testing after 28 days of curing, including weight loss, water absorption and strength, which are directly related to the durability aspect of concrete.

It has been observed that the addition of GNP to concrete mixes reduces the weight loss and pore size distribution and enhances tensile and compressive strength of concrete, thereby increasing the durability of concrete in unfavorable circumstances like freeze-thaw i.e. alternate hot and cold weather conditions.

This investigation presents original piece of experimental work conducted on modified concrete (GNP-based concrete). The aim is to construct the civil infrastructure in deep-cold region with increased life span and better performance.

As a clean and renewable energy source, wind energy will become one of the main sources of new energy supply in the future. Relying on the stable and strong wind resources at sea, wind energy has great potential to become the primary energy. As a critical part of the wind turbine, the gearbox of a wind turbine often bears a large external load. Especially at sea, due to the effects of ocean corrosion, waves and wind, the burden of the wind turbine gearbox is greater, which brings great challenges to its reliability analysis. This study aims to systematically review the reliability research in wind turbine gearboxes and guide future research directions and challenges.

This study systematically reviews some design requirements and reliability analysis methods for wind turbine gearboxes. Then, it summarizes previous studies on wind load uncertainty modeling methods, including the processing of wind measurement data and the summary of three different classifications of random wind speed prediction models. Finally, existing reliability analysis studies on two major parts of the gearbox are described and summarized.

First, the basic knowledge of wind turbine gearboxes and their reliability analysis is introduced. The requirements and reliability analysis methods of wind turbine gearboxes are explained. Then, the processing methods of wind measurement data and three different random wind speed prediction models are described in detail. Furthermore, existing reliability analysis studies on two common parts of wind turbine gearboxes, gears and bearings, are summarized and classified, including a summary of bearing failure modes. Finally, three possible future research directions for wind turbine gearbox reliability analysis are discussed, namely, reliability research under the influence of multiple factors on gears, damage indicators of bearing failure modes and quantitative evaluation criteria for the overall dynamic characteristics of offshore wind turbine gearboxes and a summary is also given.

This paper aims to systematically introduce the relevant contents of wind turbine gearboxes and their reliability analysis. The contents of wind speed data processing, predictive modeling and reliability analysis of major components are also comprehensively reviewed, including the classification and principle introduction of these contents.

Auxetic sandwich structures are gaining attention because of the negative Poisson’s ratio effect offered by these structures. Re-entrant core was one configuration of the auxetic structures. There is a growing concern about the design and behavior of re-entrant cores in aerospace, marine and protection applications. Several researchers proposed various designs of re-entrant core sandwiches with various materials. The purpose of this study is to review the most recent advances in re-entrant core sandwich structures. This review serves as a guide for researchers conducting further research in this wide field of study.

The re-entrant core sandwich structures were reviewed in terms of their design improvements, impact and quasi-static crushing responses. Several design improvements were reviewed including 2D cell, 3D cell, gradient, hierarchical and hybrid configurations. Some common applications of the re-entrant core sandwiches were given at the end of this paper with suggestions for future developments in this field.

Generally, the re-entrant configuration showed improved energy absorption and impact response among auxetic structures. The main manufacturing method for re-entrant core manufacturing was additive manufacturing. The negative Poisson’s ratio effect of the re-entrant core provided a wide area of research.

Generally, re-entrant cores were mentioned in the review articles as part of other auxetic structures. However, in this review, the focus was solely made on the re-entrant core sandwiches with their mechanics.

This study aims to develop an automatic lane-change mechanism on highways for self-driving articulated trucks to improve traffic safety.

The authors proposed a novel safety lane-change path planning and tracking control method for articulated vehicles. A double-Gaussian distribution was introduced to deduce the lane-change trajectories of tractor and trailer coupling characteristics of intelligent vehicles and roads. With different steering and braking maneuvers, minimum safe distances were modeled and calculated. Considering safety and ergonomics, the authors invested multilevel self-driving modes that serve as the basis of decision-making for vehicle lane-change. Furthermore, a combined controller was designed by feedback linearization and single-point preview optimization to ensure the path tracking and robust stability. Specialized hardware in the loop simulation platform was built to verify the effectiveness of the designed method.

The numerical simulation results demonstrated the path-planning model feasibility and controller-combined decision mechanism effectiveness to self-driving trucks. The proposed trajectory model could provide safety lane-change path planning, and the designed controller could ensure good tracking and robust stability for the closed-loop nonlinear system.

This is a fundamental research of intelligent local path planning and automatic control for articulated vehicles. There are two main contributions: the first is a more quantifiable trajectory model for self-driving articulated vehicles, which provides the opportunity to adapt vehicle and scene changes. The second involves designing a feedback linearization controller, combined with a multi-objective decision-making mode, to improve the comprehensive performance of intelligent vehicles. This study provides a valuable reference to develop advanced driving assistant system and intelligent control systems for self-driving articulated vehicles.