Search

Vehicular emission models play a key role in the development of reliable air quality modeling systems. To minimize uncertainties associated with these models, it is essential to match the high-resolution requirements of emission models with up-to-date information. However, these models are usually based on average trip speed, not on environmental parameters like ambient temperature, and vehicle’s motion characteristics, such as speed, acceleration, load and power. This contributes to the degradation of its predictive performance. In this paper, we propose to use the non-parametric Classification and Regression Trees (CART), the Boosting Multivariate Adaptive Regression Splines (BMARS) algorithm and a combination of them in hybrid models to improve the accuracy of vehicular emission prediction using on-board measurements and the chassis dynamometer testing. The experimental comparison between the proposed CART-BMARS hybrid model with the BMARS and artificial neural networks (ANNs) algorithms demonstrates its effectiveness and efficiency in estimating vehicular emissions. [ABSTRACT FROM AUTHOR]

Assessment of air pollutant profiles by using measurements involves some limitations in the implementation. For this, deterministic air quality models are often used. However, its simulation usually needs high computational requirements due to complex chemical reactions involved. In this paper, a neural network-based metamodel approach is used in conjunction with a deterministic model and some measured data to approximate the non-linear ozone concentration relationship. For this, algorithms for performance enhancement of a radial basis function neural network (RBFNN) are developed. The proposed method is then applied to estimate the spatial distribution of ozone concentrations in the Sydney basin. The experimental comparison between the proposed RBFNN algorithm and the conventional RBFNN algorithm demonstrates the effectiveness and efficiency in estimating the spatial distribution of ozone level. [ABSTRACT FROM AUTHOR]

The paper addresses the modeling and optimal control problem of a new hybrid solar-assisted air conditioning system developed for performance enhancement and energy efficiency improvement. To regulate the mass flow rate of the refrigerant vapor passing through a water storage tank for increasing the refrigerant's sub-cooling process at partial loads, we propose a new discharge bypass line together with an inline solenoid valve, installed after the compressor. In addition, to control the air flow rate, a variable speed drive is coupled with the condenser fan. For the control purpose, a lumped parameter model is first developed to describe the system dynamics in an explicit input–output relationship; then, a linear optimal control scheme is applied for the system's multivariable control. The system has been fully-instrumented to examine its performance under different operation conditions. The system model is then validated by extensive experimental tests. Based on the obtained dynamic model, an optimal controller is designed to minimize a quadratic cost function. Numerical algorithms, implemented in a simulation tool, are then employed to predict the energy performance of the system under transient loads. The experimental results obtained from implementation with PLC demonstrate that the newly-developed system can deliver higher system efficiency owing to amelioration of the refrigeration effect in the direct expansion evaporator and adjustment of its air flow rate. The development is thus promising for improvement of energy efficiency, enhancement of the system performance while fulfilling the cooling demand. [ABSTRACT FROM AUTHOR]

Along with increasing innovations in frontier engineering sciences, the advancement in Robotic Autonomous Systems (RAS) has brought about a new horizon in earthmoving processes for construction. In the military domain, there is also an increasing interest in utilising RAS technologies. In particular, ground-based forces are frequently called upon to conduct earthmoving tasks as part of military operations, tasks which could be partially or fully aided by the employment of RAS technologies. There have been rapid developments in military construction automation using high-mobility ground-based platforms, human-machine and machine-machine interfaces, teleoperation and control systems, data transmission systems, machine perception and manipulation capabilities, as well as advances in networked robotics and cyberphysical systems. Given these developments it is timely to undertake a comprehensive overview on the topic of interest to the research community and the authority. This paper presents an overview of the RAS development for platform-centric earthworks together with an analysis of the technical feasibility, maturity, key technical challenges, and future directions for the application of RAS technologies to earthmoving tasks of interest to the army. Core technologies for autonomous operation of construction machinery. Development of semi-autonomous and autonomous excavators. Projection of the future development of multi-platform cooperation. Unlabelled Image • Analysis of the development of RAS for platform-centric earthworks. • Application to selected military earthmoving tasks • Technology maturity evaluation of the RAS-based earthmoving development to date • RAS projection for army earthmoving via modes of control • Platform teaming and coordination trends in military earthworks. [ABSTRACT FROM AUTHOR]

To be sustainable in energy usage in the future, there are two aspects that need to be considered: the energy supply or generation and the consumption side, including the closely linked construction and building industries which consume a large amount of energy. Essential requirements for energy efficiency are to produce less greenhouse gas emissions and to rely more on renewable energy sources for future sustainability. Policies for mitigation of the environment impact are having effects on both the supply and demand. While the former requires more alternate sources in smart grids and improved technologies for carbon capture and storage, the latter involves the reduction of energy wastes and greenhouse gas (GHG) emissions as prerequisites to green certification within the construction and building sector. Thus, access to sustainable, affordable, and secure energy is one of the major global strategic priorities to maintain and improve public health, sustain economic growth, and mitigate the effects of climate change. Toward this goal, many countries, including Australia, are investing in clean, efficient, reliable energy systems for a prosperous and environmentally sustainable future. Hence, exploring various options to ensure energy security by diversification of energy sources is an important step in meeting the future requirements and delivering clean energy to different industry sectors. This paper discusses options to manage the use of energy sources in the power generation and construction industries. Options for mitigation of environmental impact and for achievement of sustainable energy usage, such as building design with BIM, are discussed. [ABSTRACT FROM AUTHOR]

In stevedoring operations, the ship-to-ship transfer of containers in open-sea is becoming an alternative way to avoid port congestion and subsequently can increase port efficiency. This process involves a large container ship or a barge, equipped with a crane, and a smaller vessel which transports containers between the ship and the harbour. However, the harsh open-sea conditions can produce exogenous disturbances to the crane system during the load transfer. Besides, the uncertainties and disturbances in the crane system may degrade the control performance. Hence, one of the requirements of offshore container cranes is to enhance robustness of the crane control system. This paper addresses the problem of robust sliding mode control for offshore container crane systems subject to bounded disturbances and uncertainties. The mathematical model of the control plant is first derived whereas the effects of ocean waves and strong winds are taken into account. Then, a robust sliding mode controller is proposed to track an optimal trajectory of the crane system during load transfer. Extensive simulation results are given to show that the proposed controller can significantly suppress the effects of disturbances from the vessel's wave- and wind-induced motion. [ABSTRACT FROM AUTHOR]

Pavement maintenance is widely thought to be critical for promoting their sustainability. It plays a pivotal role in sustainable and resilient transportation infrastructure for economic development and social inclusion improvement. Existing research mainly focuses on optimizing the maintenance strategies based on one player but ignores the inherent conflicts and complex interactions among multiplayer decision-makers. To address these issues, this research examined the problem of pavement maintenance involving the highway agency and maintenance service providers under the uncertainty of pavement conditions with the aim of optimizing maintenance strategies. A novel bilevel mathematical model was proposed to handle the inherent conflicts and complex interactions among decision-makers based on the Stackelberg game and Nash game. The goal is to obtain the Stackelberg–Nash equilibrium solution, where the highway agency, as the upper-level leader, determines the maintenance tasks, whereas the service providers, as the lower-level followers, provide the corresponding maintenance activities. To formulate this complex model, a bilevel particle swarm optimization (BLPSO) algorithm was developed for pavement maintenance. Finally, a practical case was used to demonstrate the practicality and efficiency of the proposed model. The results show that the mathematical model can provide feasible and effective pavement maintenance strategies for multiplayer decision-makers in real-world applications. • A bilevel mathematical model is proposed for dynamic long-term pavement maintenance. • Bilevel multiple decision-makers using the Stackelberg–Nash game are incorporated. • A BLPSO algorithm is developed to obtain an equilibrium maintenance strategy. • Comparative results show a significant profit increment for each decision-maker. • The model is feasible and effective for optimizing multiplayer pavement maintenance. [ABSTRACT FROM AUTHOR]

• A reinforcement learning (RL) based optimizer is proposed. • Extreme learning machine based tunneling-induced settlement prediction model is established. • Framework of hybrid RL based optimizer and machine learning algorithms is proposed. Prediction of ground responses is important for improving performance of tunneling. This study proposes a novel reinforcement learning (RL) based optimizer with the integration of deep-Q network (DQN) and particle swarm optimization (PSO). Such optimizer is used to improve the extreme learning machine (ELM) based tunneling-induced settlement prediction model. Herein, DQN-PSO optimizer is used to optimize the weights and biases of ELM. Based on the prescribed states, actions, rewards, rules and objective functions, DQN-PSO optimizer evaluates the rewards of actions at each step, thereby guides particles which action should be conducted and when should take this action. Such hybrid model is applied in a practical tunnel project. Regarding the search of global best weights and biases of ELM, the results indicate the DQN-PSO optimizer obviously outperforms conventional metaheuristic optimization algorithms with higher accuracy and lower computational cost. Meanwhile, this model can identify relationships among influential factors and ground responses through self-practicing. The ultimate model can be expressed with an explicit formulation and used to predict tunneling-induced ground response in real time, facilitating its application in engineering practice. [ABSTRACT FROM AUTHOR]