基于灰色神经网络的输油管道运行费用预测

输油管道运行费用的预测在原油运输中有着重要意义,文中将灰色预测模型与神经网络预测模型结合起来,建立灰色神经网络预测模型,对输油管道运行费用进行预测。灰色神经网络预测模型充分发挥了灰色预测模型和神经网络预测模型样本少、计算速度快的优点。计算结果表明：灰色神经网络与EBP神经网络相比,预测模型精度高,计算量小,收敛速度快。     

Collaborative Logistics from the Perspective of Road Transportation Companies

ABSTRACT

To survive under the ever increasing competitive and global pressures to operate more efficiently, transportation companies are obliged to adopt a collaborative focus. Various types of cooperative supply chain relationships have been discussed in both professional and academic literature over the last decades. However, research on horizontal cooperation in logistics remains scarce and scattered across various research domains. Companies operating at the same level of the supply chain and performing comparable logistics functions may cooperate horizontally to increase their productivity, improve their service level and enhance their market position. In this paper, the focus is on the operational planning of horizontal cooperations between road transportation carriers. Following a scientific literature review, a distinction may be made between two operational approaches to horizontal logistics collaboration: order sharing and capacity sharing. For both research streams, a detailed overview of solution techniques proposed in literature is presented. Moreover, some interesting opportunities for future research are identified.     

Short-term forecasting of high-speed rail demand: A hybrid approach combining ensemble empirical mode decomposition and gray support vector machine with real-world applications in China

Short-term forecasting of high-speed rail (HSR) passenger flow provides daily ridership estimates that account for day-to-day demand variations in the near future (e.g., next week, next month). It is one of the most critical tasks in high-speed passenger rail planning, operational decision-making and dynamic operation adjustment. An accurate short-term HSR demand prediction provides a basis for effective rail revenue management. In this paper, a hybrid short-term demand forecasting approach is developed by combining the ensemble empirical mode decomposition (EEMD) and grey support vector machine (GSVM) models. There are three steps in this hybrid forecasting approach: (i) decompose short-term passenger flow data with noises into a number of intrinsic mode functions (IMFs) and a trend term; (ii) predict each IMF using GSVM calibrated by the particle swarm optimization (PSO); (iii) reconstruct the refined IMF components to produce the final predicted daily HSR passenger flow, where the PSO is also applied to achieve the optimal refactoring combination. This innovative hybrid approach is demonstrated with three typical origin–destination pairs along the Wuhan-Guangzhou HSR in China. Mean absolute percentage errors of the EEMD-GSVM predictions using testing sets are 6.7%, 5.1% and 6.5%, respectively, which are much lower than those of two existing forecasting approaches (support vector machine and autoregressive integrated moving average). Application results indicate that the proposed hybrid forecasting approach performs well in terms of prediction accuracy and is especially suitable for short-term HSR passenger flow forecasting.     

Achieving sustainable development of supply chain by incorporating various carbon regulatory mechanisms

Nowadays, sustainability issues have received considerable attention in supply chain management because of the governmental requirements as well as expectations of the people. This paper introduces a novel supply chain network design problem to cover three dimensions of sustainability, namely economic, environmental, and social. The advantage of the presented model stems from considering the booming development aligned with reduction in environmental impact. In this paper, to achieve the mentioned benefits and to derive a more sustainable supply chain, a novel model in the presence of the most commonly used carbon policies is proposed. This paper, addresses sustainable development through imposing proper carbon regulatory mechanisms. Main contribution of this study is to consider the effect of imposing carbon policies on environmental advantages as well as improving the regional development level in a supply chain network design problem. Moreover, the shipment consolidation decisions are utilized to reduce cost as well as environmental impact. In addition, a novel mixed uncertainty approach is proposed to capture the uncertain emission parameters. The numerical examples and a case study are analyzed to evaluate the performance of the proposed models. It is concluded that, a high-growth economy with low-carbon can be made and also almost global well-being of people is ensured by applying the proposed model. Some managerial insights are provided for the enterprises of supply chains to make the most appropriate sustainable decisions. Finally, proper carbon emission policies are suggested based on the region sustainability characteristics.     

Models for optimizing transportation networks and modal split in China

This paper summarizes the research in a project entitled “The Models for Optimizing Transportation Network and Modal Split in China”. The research background, procedure, various mathematical models used in traffic demands forecasting, modal split and network design are presented with the key results. The systematic optimization approach adopted in this paper for integrated planning of transport network and the rational modal split formulation is firstly proposed in China. Finally, further discussion on the difficulties of using transport modeling techniques in Chinese conditions is given.     

Comparison of parametric and nonparametric models for traffic flow forecasting

Single point short-term traffic flow forecasting will play a key role in supporting demand forecasts needed by operational network models. Seasonal autoregressive integrated moving average (ARIMA), a classic parametric modeling approach to time series, and nonparametric regression models have been proposed as well suited for application to single point short-term traffic flow forecasting. Past research has shown seasonal ARIMA models to deliver results that are statistically superior to basic implementations of nonparametric regression. However, the advantages associated with a data-driven nonparametric forecasting approach motivate further investigation of refined nonparametric forecasting methods. Following this motivation, this research effort seeks to examine the theoretical foundation of nonparametric regression and to answer the question of whether nonparametric regression based on heuristically improved forecast generation methods approach the single interval traffic flow prediction performance of seasonal ARIMA models.     

Build-to-order supply chain network design under supply and demand uncertainties

Supply chain disruptions are unintended, unwanted situations resulting in a negative supply chain performance. We study the supply chain network design under supply and demand uncertainty with embedded supply chain disruption mitigation strategies, postponement with downward substitution, centralized stocking and supplier sourcing base. We designed an integrated supply-side, manufacturing and demand-side operations network in such that the total expected operating cost is minimized. We modeled it in a deterministic equivalent formulation. An L-shaped decomposition with an additional decomposition step in the master problem is proposed. The computational results showed that parallel sourcing has a cost advantage against single sourcing under supply disruptions. In addition, the build-to-order (BTO) manufacturing mitigation process has its greatest impact with high variations on demands and is integrated with the component downward substitution. Lastly, the manufacturer needs to order differentiated components to cover its requirement for maximal product demand to prevent the loss of sale, even with fewer modules in stock.     

Scheduling railway freight delivery appointments using a bid price approach

This paper proposes a method for establishing aggressive but achievable delivery appointment times for railroad shipments, taking into account individual customer needs and forecasted available train capacity. The concept of scheduling appointment times is directly patterned after current motor carrier industry practice, so that customers can plan for rail or truck deliveries in the same way.A shipment routing problem is decomposed into a deterministic “dynamic car scheduling” (DCS) process for shipments already accepted and a stochastic “train segment pricing” (TSP) process for forecasting future demands which have not yet called in and for which delivery appointments have yet to be scheduled. Both are formulated as multi-commodity network flow (MCNF) problems, where each shipment is treated as a separate commodity. Gain coefficients represent recapture probabilities that a specific customer will accept a carrier’s service offer.A comparison with a widely used revenue management formulation is given. A Lagrangian heuristic for obtaining a primal solution is also described. The problem is solved within a 1% gap using the subgradient algorithm.     

Joint optimization of freight facility location and pavement infrastructure rehabilitation under network traffic equilibrium

Establishment of industry facilities often induces heavy vehicle traffic that exacerbates congestion and pavement deterioration in the neighboring highway network. While planning facility locations and land use developments, it is important to take into account the routing of freight vehicles, the impact on public traffic, as well as the planning of pavement rehabilitation. This paper presents an integrated facility location model that simultaneously considers traffic routing under congestion and pavement rehabilitation under deterioration. The objective is to minimize the total cost due to facility investment, transportation cost including traffic delay, and pavement life-cycle costs. Building upon analytical results on optimal pavement rehabilitation, the problem is formulated into a bi-level mixed-integer non-linear program (MINLP), with facility location, freight shipment routing and pavement rehabilitation decisions in the upper level and traffic equilibrium in the lower level. This problem is then reformulated into an equivalent single-level MINLP based on Karush–Kuhn–Tucker (KKT) conditions and approximation by piece-wise linear functions. Numerical experiments on hypothetical and empirical network examples are conducted to show performance of the proposed algorithm and to draw managerial insights.     

Path flow estimator for planning applications in small communities

This paper presents an alternative planning framework to model and forecast network traffic for planning applications in small communities, where limited resources debilitate the development and applications of the conventional four-step travel demand forecasting model. The core idea is to use the Path Flow Estimator (PFE) to estimate current and forecast future traffic demand while taking into account of various field and planning data as modeling constraints. Specifically, two versions of PFE are developed: a base year PFE for estimating the current network traffic conditions using field data and planning data, if available, and a future year PFE for predicting future network traffic conditions using forecast planning data and the estimated base year origin–destination trip table as constraints. In the absence of travel survey data, the proposed method uses similar data (traffic counts and land use data) as a four-step model for model development and calibration. Since the Institute of Transportation Engineers (ITE) trip generation rates and Highway Capacity Manual (HCM) are both utilized in the modeling process, the analysis scope and results are consistent with those of common traffic impact studies and other short-range, localized transportation improvement programs. Solution algorithms are also developed to solve the two PFE models and integrated into a GIS-based software called Visual PFE. For proof of concept, two case studies in northern California are performed to demonstrate how the tool can be used in practice. The first case study is a small community of St. Helena, where the city’s planning department has neither an existing travel demand model nor the budget for developing a full four-step model. The second case study is in the city of Eureka, where there is a four-step model developed for the Humboldt County that can be used for comparison. The results show that the proposed approach is applicable for small communities with limited resources.     

The station-free sharing bike demand forecasting with a deep learning approach and large-scale datasets

The station-free sharing bike is a new sharing traffic mode that has been deployed in a large scale in China in the early 2017. Without docking stations, this system allows the sharing bike to be parked in any proper places. This study aimed to develop a dynamic demand forecasting model for station-free bike sharing using the deep learning approach. The spatial and temporal analyses were first conducted to investigate the mobility pattern of the station-free bike sharing. The result indicates the imbalanced spatial and temporal demand of bike sharing trips. The long short-term memory neural networks (LSTM NNs) were then developed to predict the bike sharing trip production and attraction at TAZ for different time intervals, including the 10-min, 15-min, 20-min and 30-min intervals. The validation results suggested that the developed LSTM NNs have reasonable good prediction accuracy in trip productions and attractions for different time intervals. The statistical models and recently developed machine learning methods were also developed to benchmark the LSTM NN. The comparison results suggested that the LSTM NNs provide better prediction accuracy than both conventional statistical models and advanced machine learning methods for different time intervals. The developed LSTM NNs can be used to predict the gap between the inflow and outflow of the sharing bike trips at a TAZ, which provide useful information for rebalancing the sharing bike in the system.     

Recent developments in national and international freight transport models within Europe

The past decade has seen many new freight transport models for use in transport planning by public authorities. Some of these models have developed new concepts, such as logistics modules, inclusion of transshipments, storage and sourcing and the determination of shipment size. This paper provides a review of the European literature on freight transport models that operate at the national or international level and have been developed since 2004. The introduction of elements of logistics thinking is identified as a common theme in recently developed models, and further worked out. Furthermore, ideas on what might be the next key developments in freight transport modelling are presented.     

Multi-period planning of closed-loop supply chain with carbon policies under uncertainty

Climate change and greenhouse gases emissions have caused countries to implement various carbon regulatory mechanisms in some industrial sectors around the globe to curb carbon emissions. One effective method to reduce industry environmental footprint is the use of a closed-loop supply chain (CLSC). The decision concerning the design and planning of an optimal network of the CLSC plays a vital role in determining the total carbon footprint across the supply chain and also the total cost. In this context, this research proposes an optimization model for design and planning a multi-period, multi-product CLSC with carbon footprint consideration under two different uncertainties. The demand and returns uncertainties are considered by means of multiple scenarios and uncertainty of carbon emissions due to supply chain related activities are considered by means of bounded box set and solve using robust optimization approach. The model extends further to investigate the impact of different carbon policies such as including strict carbon cap, carbon tax, carbon cap-and-trade, and carbon offset on the supply chain strategic and operational decisions. The model captures trade-offs that exist among supply chain total cost and carbon emissions. Also, the proposed model optimizes both supply chain total cost and carbon emissions across the supply chain activities. The numerical results reveal some insightful observations with respect to CLSC strategic design decisions and carbon emissions under various carbon policies and at the end we highlighted some managerial insights.     

Optimal competitive freight network design as hierarchical variational inequalities programming problems

Freight networks are a case of systems that multiple participants are composing interrelations along the complete supply chain. Their interrelations correspond to alternative behavior, namely, cooperation, non-cooperation and competition, while they are large-scale spatially distributed systems combining multiple means of transportation and the infrastructure and equipment typically utilized for servicing demand, results to a complex system integration. In this paper, the case of the optimal design of freight networks is investigated, aiming to highlight the particularities emerging in this case of transportation facilities strategic and/or operational planning and the multiple game-theoretic and equilibrium problems that are structured in cascade and in hierarchies. The application that is investigated here focuses in the design of a significant ‘player’ of the freight supply chain, namely container terminals, while the proposed framework will aim on analyzing investment strategies built on integrated demand–supply models and the optimal network design format. The approach will build on the multilevel Mathematical Programming with Equilibrium Constraints (MPECs) formulation, but is further extended to cope with the properties introduced by the ‘designers’ (infrastructure authorities), shippers and carriers competition in all levels of MPECs. Since container terminals are typically competing each other, the nomenclature used here for formulating appropriate MPECs problems are based on hierarchies of Variational Inequalities (VI) problems, able to capture the alternative relationships emerging in realistic freight supply chains. The proposed formulations of the competitive network design case is addressed by a novel approach of co-evolutionary agents, which can be regarded as new in equilibrium estimation. Finally, the results are compared with alternative network design cases, namely the centralized cooperative and exchanging design. Under this analysis it is able to highlight the differences among alternative design cases, but moreover an estimation of the ‘price of anarchy’ in transportation systems design is offered, an element of both theoretical as well as practical relevance.     

Integrated model for traffic flow forecasting under rainy conditions

Inclement weather, such as heavy rain, significantly affects road traffic flow operation, which may cause severe congestion in road networks in cities. This study investigates the effect of inclement weather, such as rain events, on traffic flow and proposes an integrated model for traffic flow parameter forecasting during such events. First, an analysis of historical observation data indicates that the forecasting error of traffic flow volume has a significant linear correlation with mean precipitation, and thus, forecasting accuracy can be considerably improved by applying this linear correlation to correct forecasting values. An integrated online precipitation‐correction model was proposed for traffic flow volume forecasting based on these findings. We preprocessed precipitation data transformation and used outlier detection techniques to improve the efficiency of the model. Finally, an integrated forecasting model was designed through data fusion methods based on the four basic forecasting models and the proposed online precipitation‐correction model. Results of the model validation with the field data set show that the designed model is better than the other models in terms of overall accuracy throughout the day and under precipitation. However, the designed model is not always ideal under heavy rain conditions. Copyright © 2016 John Wiley & Sons, Ltd.     

Hybrid artificial neural network and locally weighted regression models for lane-based short-term urban traffic flow forecasting

ABSTRACT

In recent years, there has been considerable research interest in short-term traffic flow forecasting. However, forecasting models offering a high accuracy at a fine temporal resolution (e.g. 1 or 5?min) and lane level are still rare. In this study, a combination of genetic algorithm, neural network and locally weighted regression is used to achieve optimal prediction under various input and traffic settings. The genetically optimized artificial neural network (GA-ANN) and locally weighted regression (GA-LWR) models are developed and tested, with the former forecasting traffic flow every 5-min within a 30-min period and the latter for forecasting traffic flow of a particular 5-min period of each for four lanes of an urban arterial road in Beijing, China. In particular, for morning peak and off-peak traffic flow prediction, the GA-ANN 5-min traffic flow model results in average errors of 3–5% and most 95th percentile errors of 7–14% for each of the four lanes; for the peak and off-peak time traffic flow predictions, the GA-LWR 5-min traffic flow model results in average errors of 2–4% and most 95th percentile errors are lower than 10% for each of the four lanes. When compared to previous models that usually offer average errors greater than 6–15%, such empirical findings should be of interest to and instrumental for transportation authorities to incorporate in their city- or state-wide Advanced Traveller Information Systems (ATIS).     

A disaggregate stochastic freight transport model for Sweden

Transportation - This paper presents estimation results for models of transport chain and shipment size choice, as well as an implementation of the estimated disaggregate models (for two commodity...     

基于灰色马尔可夫理论的油气管道腐蚀剩余寿命预测

以灰色理论的标准GM（1,1）模型和马尔可夫TPM理论为基础,提出了基于灰色马尔可夫理论的油气管道腐蚀剩余寿命预测方法。利用灰色马尔可夫理论预测腐蚀油气管道剩余寿命的步骤主要包括：最大允许腐蚀深度的确定,腐蚀速率的预测以及剩余寿命预测。并基于该方法,采用VB系统开发了实用软件,简便可靠。该方法可以在腐蚀速率波动比较大的情况下预测油气管道的剩余寿命,为油气管道腐蚀检测周期的确定提供了科学依据。     

Optimal shipment decisions for an airfreight forwarder: Formulation and solution methods

We study the freight forwarder’s shipment planning problem in an airfreight forwarding network where a set of cargo shipments have to be transported to given destinations. We provide mixed integer programming formulations that use piecewise-linear cargo rates and account for volume and weight constraints, flight departure/arrival times, as well as shipment-ready times.After exploring the solution of such models using CPLEX, we devise two solution methodologies to handle large problem sizes. The first is based on Lagrangian relaxation, where the problems decompose into a set of knapsack problems and a set of network flow problems. The second is a local branching heuristic that combines branching ideas and local search. The two approaches show promising results in providing good quality heuristic solutions within reasonable computational times, for difficult and large shipment consolidation problems.