Search

Accurately predicting train running times (TRTs) during disturbances is crucial for effective timetable rescheduling. Previous studies on train running prediction have overlooked the detailed textual description of disturbance events. To improve the prediction accuracy, this paper proposes a hybrid neural network model consisting of a transformer encoder and a fully connected neural network (FCNN) to predict the TRTs under disturbances, which is called transformer-FCNN here. In the proposed transformer-FCNN architecture, a transformer encoder is used to process textual disturbance events, while FCNN is used to deal with static features. The performance of transformer-FCNN is validated using data from the Wuhan-Guangzhou and Xiamen-Shenzhen high-speed railways. The results show that the models considering the disturbance category can substantially improve the predictive performance compared with those that do not. Further, based on the same algorithm, models which use textual disturbance event records are shown to reduce the mean absolute error and the root mean squared error, respectively, by over 10.8% and 8.3% on average compared with those that only consider the disturbance category. The proposed model can support potential strategies of train operation control, by providing accurate prediction results. [ABSTRACT FROM AUTHOR]

Railway alignment optimization in earthquake‐prone mountainous (EPM) regions should quantify and trade off construction investments and seismic risks. Unfortunately, slight attention has been previously devoted to this trade‐off. To this end, based on the FEMA‐P58 methodology, a net present value (NPV) model of risk avoidance is presented and solved. In the model, alignment alternatives are first segmented into structural groups with different probabilistic seismic fragility curves, which are then used to generate structural repair cost and repair time curves. Afterward, a probabilistic seismic hazard curve is introduced to estimate the expected annual repair cost and time for computing railway direct and indirect seismic losses. Hence, the railway total annual loss caused by seismic activity can be obtained. Next, a benefit–cost analysis is performed to combine construction cost and seismic loss as the risk‐cost NPV. To optimize this objective function, a particle swarm algorithm is used as the basic approach. For implementing the probabilistic seismic performance analysis, a Monte Carlo simulation (MCS) is employed as the risk assessment module. Furthermore, due to the computationally intensive nature of MCS, a CPU‐based parallelization is embedded into the algorithm to expedite the search. Finally, the proposed model and method are applied to a representative real‐world railway case in an EPM region. Their effectiveness is discussed and verified in five experiments, including algorithm convergence analysis, alignment solution comparison, seismic risk interpretation, computational efficiency test, and a specific sensitivity analysis. [ABSTRACT FROM AUTHOR]

Vertical alignment reconstruction obtains alignment parameters by fitting geometric components to a set of measured points representing the profile of an existing road or railroad, which is essential in alignment consistency analysis and maintenance to ensure safety and comfort. The neural dynamics model of Adeli and Park is explored and improved for reconstructing vertical alignments with constraints. The structure of the dynamics model is modified to include three layers: parameter layer, intermediate layer, and energy layer. The number of nodes in the parameter or intermediate layers corresponds to the number of independent parameters defining a vertical alignment. The number of nodes in the energy layer is the sum of the number of deviations and the number of constraints in the alignment reconstruction problem. The coefficients connecting nodes between the parameter layer and the intermediate layer determine the integral operations, which define the Levenberg–Marquardt algorithm of the dynamics model (LMADM) and the steepest descent algorithm of the dynamics model (SDADM). Both the LMADM and SDADM methods satisfy the Lyapunov stability theorem, but the LMADM method outperforms the SDADM method in its objective function value and computation time. Experiment results demonstrate that there are multiple local optima for a vertical alignment reconstruction, and the solutions obtained by the LMADM method are the best obtained so far, compared with those reported in the literature, with 57.1% and 23.4% decreases of the mean squared error for the highway and the railroad examples, respectively. [ABSTRACT FROM AUTHOR]

This study investigates the spatiotemporal distribution of electric vehicle (EV) charging demands and operating efficiency of the charging system. The travel behavior of EV drivers is analyzed by considering the heterogeneity of range anxiety and bound rationality. Building on existing charging choice models, our more holistic perspective of charging demand distribution is obtained through multiagent system (MAS) modeling. In our study, the charging demand distribution in different areas is compared by considering two charging price schemes. The performance of the charging system is then evaluated based on three indicators, the charging request rejection rate, charging pile utilization rate, and charging load deviation, thereby verifying the effectiveness of our charging demand prediction model. This is done using multiagent-based simulations applied to the National Household Travel Survey (NHTS) 2017 dataset. The results are analyzed according to different key indicators, mainly indicating (a) the limitations of the time-of-use (TOU) pricing strategy in reducing the peak-valley difference, (b) the transferability of charging demand among different functional areas, and (c) that there is less demand for charging piles in the workplace, as users mainly rely on home charging. These results facilitate further analyses to help the design and operation of the EV charging infrastructure., Author(s): Shuai Ling [1]; Xiang Zhu [1]; Qing Wang (corresponding author) [2]; Paul Schonfeld [3] 1. Introduction Innovative transportation technologies have emerged continuously in recent years. Electric vehicles (EVs) have [...]

Mountain railway alignment optimization has always been a challenge for designers and researchers in this field. It is extremely difficult for existing methods that optimize alignments before major structures to generate a better alignment than the best one provided by human designers when the terrain is drastically undulating between the start and endpoints. To fill this gap, a "structures before alignments" design process is proposed in this paper. Primarily, a landform recognition method is devised for recognizing dominating landforms. Then, a bi‐level alignment optimization model is proposed, with the upper level dedicated to characterizing dominating structures and the lower level focusing on optimizing the entire alignments. To solve this bi‐level model, a three‐stage optimization method is designed. At the first stage, a scanning process and screening operators are devised for generating all the possible locations of dominating structures. At the second stage, a hierarchical multi‐criteria decision‐making procedure is applied for selecting the optimized dominating structure layouts. At the third stage, alignments are optimized based on the determined structure layouts using a bi‐objective optimization method, which minimizes construction cost and geo‐hazard risk simultaneously. The proposed model and solution method are applied to two real‐world cases whose results verify their capabilities in producing alignment alternatives with better combinations of construction cost and geo‐hazard risk than manually designed alternatives. [ABSTRACT FROM AUTHOR]

Reasonable earthmoving-equipment combinations have helped to reduce duration and cost in the construction industry traditionally. However, reducing carbon emissions in earthmoving operations is highly desirable because earthmoving operations involve a large number of heavy equipment, which produce high carbon emissions. It is necessary to study a novel equipment combination optimization model considering decreasing carbon emissions in addition to duration and cost. Hence, a triobjective equipment combination optimization (ECO) model is developed, minimizing carbon emissions as well as project duration and cost. In this model, the excavation and transportation processes of earthwork are regarded as a queuing system, and queuing theory is integrated directly into the model to compute the involved parameters instead of a simulation. On the other hand, for obtaining the optimal solution set of the multiobjective problems with more objectives, a novel two-archive multiobjective particle swarm algorithm is proposed, which updates individuals in archives by not only Pareto domination but also an indicator that can assess solution quality. A real case study demonstrated that the model can efficiently provide a reasonable earthmoving-equipment combination considering the trade-off among carbon emissions, duration, and cost for managers. A multiobjective model for obtaining the optimal earthmoving-equipment combination is proposed in this paper. In addition to traditional reductions in duration and cost, the model also considers sustainability requirements by reducing carbon emissions in the construction industry. In other words, this model can offer the solutions of equipment combinations in terms of not only reducing the cost and duration to construction managers, but also reducing carbon emissions. Instead of one combination of earthmoving equipment, a set of nondominated solutions is offered in this model, and this allows managers to make choices based on specific site conditions. In addition, the authors have improved the traditional algorithm to obtain the solutions to better meet the needs of users. This new earthmoving-equipment combination optimization model can quickly get reasonable equipment combinations and helps minimize carbon emissions as well as duration and cost. This model has been applied to a real earthwork project in China and gave the optimal excavator-truck configuration that satisfied the contractor. [ABSTRACT FROM AUTHOR]