Microscopic Models and Network Transformations for Automated Railway Traffic Planning

This article tackles the real‐world planning problem of railway operations. Improving the timetable planning process will result in more reliable product plans and a higher quality of service for passengers and freight operators. We focus on the microscopic models for computing accurate track blocking times for guaranteeing feasibility and stability of railway timetables. A conflict detection and resolution model manages feasibility by identifying conflicts and computing minimum headway times that provide conflict‐free services. The timetable compression method is used for computing capacity consumption and verifying the stability according to the UIC Capacity Code 406. Furthermore, the microscopic models have been incorporated in a multilevel timetabling framework for completely automated generation of timetables. The approach is demonstrated in a real‐world case study from the Dutch railway network. Practitioners can use these microscopic timetabling models as an important component in the timetabling process to improve the general quality of timetables.     

Optimizing Passenger Flow Control and Bus‐Bridging Service for Commuting Metro Lines

Oversaturated conditions are often observed during peak‐hour periods, especially for commuting metro lines serving as a corridor connecting suburb and urban areas due to its unidirectional passenger flow pattern. System operators are concerned about the amount of passengers accumulated inside station and at platform when train service cannot meet the travel demand. In this article, we tackle the metro system congestion issue and develop a compound strategy integrating passenger flow control and bus‐bridging service, to mitigate overcrowded situation. A two‐stage mathematical modeling procedure is proposed. Stage 1 determines the stations and time periods for taking passenger flow control strategy. Stage 2 identifies the optimal bus‐bridging services. Mixed integer linear programming models are developed to find the demand‐responsive flow control pattern and bus‐bridging services. The proposed passenger flow control and bus‐bridging strategy is applied to a commuting metro line in Shanghai. The results show that the proposed strategy is effective in reducing the number of stranded passengers, releasing the overcrowding pressure, and improving passengers’ satisfaction.     

Dynamic origin‐destination flow estimation using automatic vehicle identification data: A 3D convolutional neural network approach

Dynamic origin‐destination (OD) flow estimation is one of the most fundamental problems in traffic engineering. Despite numerous existing studies, the OD flow estimation problem remains challenging, as there is large dimensional difference between the unknown values to be estimated and the known traffic observations. To meet the needs of active traffic management and control, accurate time‐dependent OD flows are required to understand time‐of‐day traffic flow patterns. In this work, we propose a three‐dimensional (3D) convolution‐based deep neural network, “Res3D,” to learn the high‐dimensional correlations between local traffic patterns presented by automatic vehicle identification observations and OD flows. In this paper, a practical framework combining simulation‐based model training and few‐shot transfer learning is introduced to enhance the applicability of the proposed model, as continuously observing OD flows could be expensive. The proposed model is extensively tested based on a realistic road network, and the results show that for significant OD flows, the relative errors are stable around 5%, outperforming several other models, including prevalent neural networks as well as existing estimation models. Meanwhile, corrupted and out‐of‐distribution samples are generated as real‐world samples to validate Res3D's transferability, and the results indicated a 60% improvement with few‐shot transfer learning. Therefore, this proposed framework could help to bridge the gaps between traffic simulations and empirical cases.     

New method for modal identification of super high‐rise building structures using discretized synchrosqueezed wavelet and Hilbert transforms

Measured signals obtained by sensors during dynamic events such as earthquake, wind, and wave contain nonlinear, nonstationary, and noisy properties. In this paper, a new approach is presented for modal parameter identification of structures particularly suitable for very large real‐life structures such as super high‐rise building structures based on the integration of discretized synchrosqueezed wavelet transform, the Hilbert transform, and the linear least‐square fit. Its effectiveness is demonstrated first by application to a two‐dimensional frames from the literature, and then to the 123‐story Lotte World Tower (LWT) under construction in Seoul, Korea. The LWT measurements are very low‐amplitude ambient vibrations. Extracting the natural frequencies and damping ratios from such low‐amplitude signals are known to be very challenging. Further, the new methodology was compared with the empirical mode decomposition. It is demonstrated that the new method is capable of extracting both natural frequencies and damping rations from low‐amplitude signals effectively and with a higher accuracy compared with the empirical mode decomposition approach. The results of this research indicate a super high‐rise building like LWT has a damping ratio in the range 0.7–3.4%. The new method is quite promising for practical implementations of health monitoring of large real‐life structures.     

Relay Requirement and Traffic Assignment of Electric Vehicles

This article defines, formulates, and solves a new equilibrium traffic assignment problem with side constraints—the traffic assignment problem with relays. The relay requirement arises from the driving situation that the onboard fuel capacity of vehicles is lower than what is needed for accomplishing their trips and the number and distribution of refueling infrastructures over the network are under the expected level. We proposed this problem as a modeling platform for evaluating congested regional transportation networks that serve plug‐in electric vehicles (in addition to internal combustion engine vehicles), where battery‐recharging or battery‐swapping stations are scarce. Specifically, we presented a novel nonlinear integer programming formulation, analyzed its mathematical properties and paradoxical phenomena, and suggested a generalized Benders decomposition framework for its solutions. In the algorithmic framework, a gradient projection algorithm and a labeling algorithm are adopted for, respectively, solving the primal problem and the relaxed master problem—the shortest path problem with relays. The modeling and solution methods are implemented for solving a set of example network problems. The numerical analysis results obtained from the implementation clearly show how the driving range limit and relay station location reshape equilibrium network flows.     

Joint power distribution and charging network design for electrified mobility with user equilibrium decisions

Rapid adoption of electric vehicles (EVs) requires the development of a highly flexible charging network. The design and management of the charging infrastructure for EV-dominated transportation systems are intertwined with power grid operations both economically and technically. High penetration of EVs in the future can increase the charging loads and cause a wide range of operational issues in power distribution networks (PDNs). This paper aims to design an EV charging network with an embedded PDN layout to account for energy dispatch and underlying traffic flows in urban transportation networks supporting electric mobility in the near future. A mixed-integer bilevel model is proposed with the EV charging facility location and PDN energy decisions in the upper level and user equilibrium traffic assignment in the lower level considering an uncertain charging demand. The objective is to minimize the cost of PDN operations, charging facility deployments, and transportation. The proposed problem is solved using a column and constraint generation (C&CG ) algorithm, while a macroscopic fundamental diagram concept is implemented to estimate the arc travel times. The methodology is applied to a hypothetical and two real-world case study networks, and the solutions are compared to a Benders decomposition benchmark. The east-coast analysis results indicate a 77.3% reduction in the computational time. Additionally, the benchmark technique obtains an optimality gap of 1.15%, while the C&CG algorithm yields a 0.61% gap. The numerical experiments show the robustness of the proposed methodology. Besides, a series of sensitivity analyses has been conducted to study the impact of input parameters on the proposed methodology and draw managerial insights.     

Hybrid Time‐Frequency Blind Source Separation Towards Ambient System Identification of Structures

Abstract: Ambient system identification in noisy environments, in the presence of low‐energy modes or closely‐spaced modes, is a challenging task. Conventional blind source separation techniques such as second‐order blind identification (SOBI) and Independent Component Analysis (ICA) do not perform satisfactorily under these conditions. Furthermore, structural system identification for flexible structures require the extraction of more modes than the available number of independent sensor measurements. This results in the estimation of a non‐square modal matrix that is spatially sparse. To overcome these challenges, methods that integrate blind identification with time‐frequency decomposition of signals have been previously presented. The basic idea of these methods is to exploit the resolution and sparsity provided by time‐frequency decomposition of signals, while retaining the advantages of second‐order source separation methods. These hybrid methods integrate two powerful time‐frequency decompositions—wavelet transforms and empirical mode decomposition—into the framework of SOBI. In the first case, the measurements are transformed into the time‐frequency domain, followed by the identification using a SOBI‐based method in the transformed domain. In the second case, a subset of the operations are performed in the transformed domain, while the remaining procedure is conducted using the traditional SOBI method. A new method to address the under‐determined case arising from sparse measurements is proposed. Each of these methods serve to address a particular situation: closely‐spaced modes or low‐energy modes. The proposed methods are verified by applying them to extract the modal information of an airport control tower structure located near Toronto in Canada.     

A Cell‐Based Distributed‐Coordinated Approach for Network‐Level Signal Timing Optimization

This article develops an efficient methodology to optimize the timing of signalized intersections in urban street networks. Our approach distributes a network‐level mixed‐integer linear program (MILP) to intersection level. This distribution significantly reduces the complexity of the MILP and makes it real‐time and scalable. We create coordination between MILPs to reduce the probability of finding locally optimal solutions. The formulation accounts for oversaturated conditions by using an appropriate objective function and explicit constraints on queue length. We develop a rolling‐horizon solution algorithm and apply it to several case‐study networks under various demand patterns. The objective function of the optimization program is to maximize intersection throughput. The comparison of the obtained solutions to an optimal solution found by a central optimization approach (whenever possible) shows a maximum of 1% gap on a number of performance measures over different conditions.     

Integrating IoT into operational workflows for real-time and automated decision-making in repetitive construction operations

Construction operations are typically spread across large areas and require remote collaboration between multiple disparate resources—characteristics that create logistical challenges for making and automating decisions on the worksite. This paper provides a framework for leveraging the growing ubiquity of devices that can be considered part of the internet of things (IoT) to inform real-time decision-making on the construction site. Specifically, systems and control theory concepts are implemented by first synthesizing sensor information at their point of origin into resource state, and then using this state as feedback into a process model of the operation. Decisions that are programed into the process model are then made automatically based on real-time status of the operation and relayed back to the entities on the construction site through the IoT infrastructure. The real-time decision-making capabilities enabled by the presented methodology and its associated benefits to construction performance are demonstrated through the use of a virtual experimental platform that simulates a potential implementation of IoT-enabled control on the construction worksite for an earthmoving operation. This research provides a practical and sensor-agnostic implementation of operation-level decision-making by utilizing IoT networks along with advancements in modeling and simulation tools. This paper illustrates the types of insights that can be synthesized from an operations-level IoT network that gathers and transmits information in real time from various locations of the worksite. Currently and without the use of the prescribed methodology, such actionable insight would be impractical, cost-prohibitive, and even impossible to obtain.     

Optimal Fleet Size and Fare Setting in Emerging Taxi Markets with Stochastic Demand

The emerging taxi services, for instance, Uber and Lyft, are challenging traditional fully regulated taxi markets. Transportation agencies are spending significant efforts to understand the optimal pricing and fleet size taxis that are efficient for a given urban area. This study develops a modeling framework for studying a decentralized equilibrium based market study where the fare is strictly regulated by a taxi commission. The nature of demand‐supply equilibria with stochastic demand are discussed to determine optimal development strategies, for instance, number of issued licenses and fare setting. Two Stackelberg games are formulated to specify leader‐follower relationships between transportation authorities and and the followers — taxi drivers and passengers. An iterative approach is designed to simulate the games and solve corresponding mathematical optimization problems. The case study is based on New York City data which shows that the taxi market may be oversupplied and underpriced, which confirms findings from other studies and price hikes in 2012. Furthermore, different development strategies are proposed based on two Stackelberg games to respond to intended taxi system changes, such as price and quantity elasticity of taxi demand, levels of demand variance, average taxi operation speed, passengers' waiting time value, and taxi service coverage. The results have important implications in determining development strategies for taxi industry with emerging taxi services, stochastic demand, and the rapidly changing environment.     

Integrated Train Timetabling and Rolling Stock Scheduling Model Based on Time‐Dependent Demand for Urban Rail Transit

The congestion of urban transportation is becoming an increasingly critical problem for many metropolises. The Urban Rail Transit (URT) system has attracted substantial attention due to its safety, high speed, high capacity, and sustainability. With a focus on a holistic modeling framework for train scheduling problems, this article proposes a novel optimization methodology that integrates both train timetabling and rolling stock scheduling based on time‐dependent passenger flow demands. We particularly consider the tradeoff between waiting times for passengers and the train frequency of the URT system. By using train paths and rolling stock indicators as decision variables, this problem is formulated as a bi‐level programming model. A simulated‐annealing (SA)‐based heuristic algorithm is employed to solve the proposed model and generate approximate optimal solutions. In the case study of Line 10 of Beijing Subway, GAMS (The General Algebraic Modeling System) with the IBM ILOG CPLEX Optimization Studio (CPLEX) solver can barely obtain a solution in more than 2 hours, whereas the SA‐based heuristic can obtain the solution within 16 minutes and 44 seconds with the objective value improved by more than 14%. The calculation results and comparisons indicate that the SA‐based heuristic can efficiently produce approximate optimal scheduling strategies; these findings demonstrate the practical value of our proposed approaches.     

BIM-based framework for managing performance of subway stations

Rapid transit systems are considered a sustainable mode of transportation compared to other modes of transportation taking into consideration number of passengers, energy consumed and amount of pollution emitted. Building Information Modeling (BIM) is utilized in this research along with a global ranking system to monitor Indoor Environmental Quality (IEQ) in subway stations. The research is concerned with developing global rating system for subway stations' networks. The developed framework is capable of monitoring indoor temperature and Particulate Matter (PM) concentration levels in subway stations. A rating system is developed using Simos' ranking method in order to determine the weights of different components contributing to the whole level of service of a subway station as well as maintenance priority indices. A case study is presented to illustrate the use of the proposed system. The developed ranking system showed its effectiveness in ranking maintenance actions globally.     

A decomposition scheme for parallelization of system optimal dynamic traffic assignment on urban networks with multiple origins and destinations

This paper presents a decomposition scheme to find near‐optimal solutions to a cell transmission model‐based system optimal dynamic traffic assignment problem with multiple origin‐destination pairs. A linear and convex formulation is used to define the problem characteristics. The decomposition is designed based on the Dantzig–Wolfe technique that splits the set of decision variables into subsets through the construction of a master problem and subproblems. Each subproblem includes only a single origin‐destination pair with significantly less computational burden compared to the original problem. The master problem represents the coordination between subproblems through the design of interactive flows between the pairs. The proposed methodology is implemented in two case study networks of 20 and 40 intersections with up to 25 origin‐destination pairs. The numerical results show that the decomposition scheme converges to the optimal solution, within 2.0% gap, in substantially less time compared to a benchmark solution, which confirms the computational efficiency of the proposed algorithm. Various network performance measures have been assessed based on different traffic state scenarios to draw managerial insights.     

An efficient algorithm for architecture design of Bayesian neural network in structural model updating

There has been growing interest in applying the artificial neural network (ANN) approach in structural system identification and health monitoring. The learning process of neural network can be more robust when presented in the Bayesian framework, and rational architecture of the Bayesian neural network is critical to its performance. Apart from number of hidden neurons, the specific forms of the transfer functions in both hidden and output layers are also crucially important. To the best of our knowledge, however, the simultaneous design of proper number of hidden neurons, and specific forms of hidden‐ and output‐layer transfer functions has not yet been reported in terms of the Bayesian neural network. It is even more challenging when the transfer functions of both layers are parameterized instead of using fixed shape forms. This paper proposes a tailor‐made algorithm for efficiently designing the appropriate architecture of Bayesian neural network with simultaneously optimized hidden neuron number and custom transfer functions in both hidden and output layers. To cooperate with the proposed algorithm, both the Jacobian of the network function and Hessian of the negative logarithm of weight posterior are derived analytically by matrix calculus. This is much more accurate and efficient than the finite difference approximation, and also vital for properly designing the Bayesian neural network architecture as well as further quantifying the confidence interval of network prediction. The validity and efficiency of the proposed methodology is verified through probabilistic finite element (FE) model updating of a pedestrian bridge by using the field measurement data.     

A Network Generalized Extreme Value Model for Route Choice Allowing Implicit Route Enumeration

This article introduces an adaptation of the Network GEV model for modelling joint choices, named Joint Network GEV (JNG), and its application to the route choice context, named Link‐Based JNG (LB‐JNG), assuming the choice of a route as the joint choice of all links belonging to that route. The LB‐JNG model aims at reproducing the effects of routes overlapping with a theoretical robust framework (since it belongs to the Network GEV, to date the most flexible closed‐form model in reproducing covariances), allowing at the same time for easy application to real networks through a closed‐form probability statement, a proper definition of its parameters and the availability of an implicit route enumeration algorithm for network loading. The article carries out first an overview of the theoretical properties of the JNG model. Then, the LB‐JNG adaptation to route choice is described, and its capability to reproduce the effects of routes overlapping is investigated using some test networks, wherein the performances of the proposed model are also compared with those of other route choice models available in the literature. Finally, an implicit route enumeration algorithm for macroscopic static stochastic network loading, based on a double‐step generalization of Dial's STOCH algorithm, is proposed and tested on real size networks.     

A Hybrid Branch‐and‐Bound and Benders Decomposition Algorithm for the Network Design Problem

Given a set of candidate road projects associated with costs, finding the best subset with respect to a limited budget is known as the network design problem (NDP). The NDP is often cast in a bilevel programming problem which is known to be NP‐hard. In this study, we tackle a special case of the NDP where the decision variables are integers. A variety of exact solutions has been proposed for the discrete NDP, but due to the combinatorial complexity, the literature has yet to address the problem for large‐size networks, and accounting for the multimodal and multiclass traffic flows. To this end, the bilevel problem is solved by branch‐and‐bound. At each node of the search tree, a valid lower bound based on system optimal (SO) traffic flow is calculated. The SO traffic flow is formulated as a mixed integer, non‐linear programming (MINLP) problem for which the Benders decomposition method is used. The algorithm is coded on a hybrid and synchronized platform consisting of MATLAB (optimization engine), EMME 3 (transport planning module), MS Access (database), and MS Excel (user interface). The proposed methodology is applied to three examples including Gao's network, the Sioux‐Falls network, and a real size network representing the city of Winnipeg, Canada. Numerical tests on the network of Winnipeg at various budget levels have shown promising results.     

Development of a Data‐Driven Framework for Real‐Time Travel Time Prediction

Travel time prediction is one of the most important components in Intelligent Transportation Systems implementation. Various related techniques have been developed, but the efforts for improving the applicability of long‐term prediction in a real‐time manner have been lacking. Existing methods do not fully utilize the advantages of the state‐of‐the‐art cloud system and large amount of data due to computation issues. We propose a new prediction framework for real‐time travel time services in the cloud system. A distinctive feature is that the prediction is done with the entire data of a road section to stably and accurately produce the long‐term (at least 6‐hour prediction horizon) predicted value. Another distinctive feature is that the framework uses a hierarchical pattern matching called Multilevel k‐nearest neighbor (Mk‐NN) method which is compared with the conventional k‐NN method and Nearest Historical average method. The results show that the method can more accurately and robustly predict the long‐term travel time with shorter computation time.     

Multi-objective simulation-optimization for earthmoving operations

This paper presents an integrated framework of multi-objective simulation-optimization for optimizing equipment-configurations of earthmoving operations. The earthmoving operations are modeled through simulation and the performances associated with equipment-configurations are evaluated in terms of multiple attribute utility reflecting the preference of decision-makers to multiple criteria. A modified two-stage ranking-selection procedure, a statistical method, is equipped to help compare the alternatives that have random performances and thus reduce unnecessary number of simulation replications. In addition, particle swarm optimization is incorporated to search for the potential equipment-configurations to be examined through simulation, thus speeding up the evaluation process and avoiding exhaustive simulation experiments of all the alternatives. The architecture of the integrated framework is developed. A computational example is provided to justify the proposed methodology. The study will provide an alternative means to help plan earthmoving operations by considering multiple criteria and combining multiple methodologies.     

An economic valuation model for alternative pressure management schemes in water distribution networks

Pressure management (PM) is commonly used in water distribution networks (WDNs) to provide a wide range of benefits. This study presents an economic evaluation framework to support the decision-making process relating to alternative PM schemes. The methodology allows for the assessment the principal direct and indirect benefits and costs associated with using pressure-reducing valves (PRVs). The methodology is applied to a district metered area in a WDN in Mashhad, Iran, by changing the existing fixed–outlet (FO-PRV) to time-based (TM-PRV) and flow-based modulation (FM-PRV). The results indicated that FM-PRV is the most beneficial scheme for the studied case. The importance of estimating direct and indirect benefits is highlighted. The presented methodology is essential to persuade water utility decision-makers to recognize the economic feasibility and significant benefits of implementing PM schemes and justify the associated investment.     

Network-Wide Optimal Scheduling of Transit Systems Using Genetic Algorithms

The primary objective of any transit system is to provide a better level of service to its passengers. One of the good measures of level of service is the waiting time of passengers during their journey. The waiting time consists of an initial waiting time (the time a passenger waits to board a vehicle at his or her point of origin) and a transfer time (the time a passenger waits at a transfer station while transferring from one vehicle to another). An efficient schedule minimizes the overall transfer time (TT) of passengers transferring between different routes as well as the initial waiting time (IWT) of the passengers waiting to board the vehicle at their point of origin. This paper uses genetic algorithm (GA)—a search and optimization procedure—to find optimal/near-optimal schedules of vehicles in a transit network. The main advantage of using GA is that the transit network scheduling problem can be reformulated in a manner that is computationally more efficient than the original problem. Further, the coding aspect of GA inherently takes care of most of the constraints associated with the scheduling problem. Results from a number of test problems show that GAs are able to find optimal/near-optimal schedules with minimal computational resources.