Method for estimating railroad track settlements due to dynamic traffic loads

This paper is the result of real-scale physical modeling study designed to simulate the load-deformation characteristics of railroad foundation systems that include the railroad ties, the ballast, and the sub-base layers of a railroad embankment. The study presents comparisons of the application of dynamic loads of 100kN on the rails, and the resulting deformations during a 500,000 cycle testing period for three rail support systems; wood, concrete and steel. The results show that the deformation curve has an exponential shape, with the larger portion of the deformation occurring during the first 50,000 load cycles followed by a tendency to stabilize between 100,000 to 500,000 cycles. These results indicate that the critical phase of deformations of a new railroad is within the first 50,000 cycles of loading, and after that, it slowly attenuates as it approaches a stable value. The paper also presents empirically derived formulations for the estimation of the deformations of the rail supports as a result of rail traffic.

Estimation and evaluation of dynamic properties as indicators of changes on soil structure in sugarcane fields of São Paulo State - Brazil

The indiscriminate management and use of soils without moisture control has changed the structure of it due to the increment of the traffic by agricultural machines through the years, causing in consequence, a soil compaction and yield reduction in the areas of intensive traffic. The purpose of this work was to estimate and to evaluate the performance of preconsolidation pressure of the soil and shear stress as indicators of changes on soil structure in fields cropped with sugarcane, as well as the impact of management processes in an Eutrorthox soil structure located in São Paulo State. The experimental field was located in Piracicaba's rural area (São Paulo State, Brazil) and has been cropped with sugarcane, in the second harvest cycle. The soil was classified by Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA) [Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA), 1999. Centro Nacional de Pesquisa de Solos. Sistema Brasileiro de Classificao de Solos, Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA), Brasilia, 412 pp.] as an Eutrorthox. Undisturbed samples were collected and georeferenced in a grid of 60 m x 60 m from two depths: 0-0.10 m (superficial layer - SL) and in the layer of greatest mechanical resistance (LGMR), previously identified by cone index (CI). The investigated variables were pressure preconsolidation (sigma(p)), apparent cohesion (c) and internal friction angle (phi). The conclusions from the results were that the SLSC was predicted satisfactorily from up as a function of soil moisture; thus, decisions about machinery size and loading (contact pressures) can be taken. Apparent cohesion (c), internal friction angle (phi) and the Coulomb equation were significantly altered by traffic intensity. The sigma(p), c and phi maps were shown to be important tools to localize and visualize soil compaction and mechanical resistance zones. They constitute a valuable resource to evaluate the traffic impact in areas cropped with sugarcane in State of São Paulo, Brazil. (C) 2008 Elsevier B.V. All rights reserved.

Urban Traffic Control and Monitoring - An Approach for the Brazilian Intelligent Cities Project

This paper describes an urban traffic control system which aims at contributing to a more efficient traffic management system in the cities of Brazil. It uses fuzzy sets, case-based reasoning, and genetic algorithms to handle dynamic and unpredictable traffic scenarios, as well as uncertain, incomplete, and inconsistent information. The system is composed by one supervisor and several controller agents, which cooperate with each other to improve the system's results through Artificial Intelligence Techniques.

Traffic flow breakdown prediction using feature reduction through Rough-Neuro fuzzy Networks

The prediction of the traffic behavior could help to make decision about the routing process, as well as enables gains on effectiveness and productivity on the physical distribution. This need motivated the search for technological improvements in the Routing performance in metropolitan areas. The purpose of this paper is to present computational evidences that Artificial Neural Network ANN could be use to predict the traffic behavior in a metropolitan area such So Paulo (around 16 million inhabitants). The proposed methodology involves the application of Rough-Fuzzy Sets to define inference morphology for insertion of the behavior of Dynamic Routing into a structured rule basis, without human expert aid. The dynamics of the traffic parameters are described through membership functions. Rough Sets Theory identifies the attributes that are important, and suggest Fuzzy relations to be inserted on a Rough Neuro Fuzzy Network (RNFN) type Multilayer Perceptron (MLP) and type Radial Basis Function (RBF), in order to get an optimal surface response. To measure the performance of the proposed RNFN, the responses of the unreduced rule basis are compared with the reduced rule one. The results show that by making use of the Feature Reduction through RNFN, it is possible to reduce the need for human expert in the construction of the Fuzzy inference mechanism in such flow process like traffic breakdown. © 2011 IEEE.