00714944

Component

http://onlinepubs.trb.org...trr/1995/1497/1497-008.pdf

https://scholar.google.co...Teng&publication_year=1995

The train formation plan is one of the most important elements of railroad system operations. Although mathematical programming formulations and algorithms are available for solving the train formation problem (TFP), the computational time required for their convergence is usually excessive. At the same time, shorter decision intervals are becoming necessary given the highly competitive operating climates of the railroad industry. Thus, new techniques are needed for generating efficient solutions for the TFP. In this study, the authors present the development of a genetic algorithm (GA) as a possible technique for this problem. The calibration and validation of the GA model are carried out for three different complexity levels of objective functions. It is found that the optimal solutions can be found for all the different formulations while consuming only a small amount of computation time.

This paper appears in Transportation Research Record No. 1497, Artificial Intelligence and Geographical Information. Distribution, posting, or copying of this PDF is strictly prohibited without written permission of the Transportation Research Board of the National Academy of Sciences. Unless otherwise indicated, all materials in this PDF are copyrighted by the National Academy of Sciences. Copyright © National Academy of Sciences. All rights reserved

01399824

English

p. 62-69

1995

Transportation Research Record

0309061636

Figures (7) ; References (4) ; Tables (8)

Calibration; Genetic algorithms; Train makeup; Validation

Computation time

Freight Transportation; Highways; Planning and Forecasting; Railroads

TRIS, TRB

Dec 20 1995 12:00AM

• A FRAMEWORK FOR INTEGRATING GIS-T WITH KBES: A PAVEMENT MANAGEMENT SYSTEM EXAMPLE
• DESIGN OF ROUTING NETWORKS USING GEOGRAPHIC INFORMATION SYSTEMS: APPLICATIONS TO SOLID AND HAZARDOUS WASTE TRANSPORTATION PLANNING
• DEVELOPMENT OF A REGIONAL GEOGRAPHICAL INFORMATION SYSTEM FOR ITS/IVHS NETWORK
• DEVELOPMENT OF NEURAL SIGNAL CONTROL SYSTEM--TOWARD INTELLIGENT TRAFFIC SIGNAL CONTROL
• EVOLUTIONARY NEURAL NETWORK MODEL FOR THE SELECTION OF PAVEMENT MAINTENANCE STRATEGY
• GEOGRAPHIC INFORMATION SYSTEM INVENTORY DATA PREPARATION: ASSIGNING SPATIAL PROPERTIES TO HIGHWAY FEATURE FILES USING INDEPENDENT DATA SOURCES
• GEOGRAPHIC INFORMATION SYSTEMS/GLOBAL POSITIONING SYSTEMS DESIGN FOR NETWORK TRAVEL TIME STUDY
• HYBRID ARTIFICIAL INTELLIGENCE APPROACH TO CONTINUOUS BRIDGE MONITORING
• IDENTIFICATION OF HAZARDOUS HIGHWAY LOCATIONS USING KNOWLEDGE-BASED GIS: A CASE STUDY
• KNOWLEDGE ACQUISITION, REPRESENTATION, AND KNOWLEDGE BASE DEVELOPMENT OF INTELLIGENT TRAFFIC EVALUATOR FOR PROMPT INCIDENT DIAGNOSIS
• KNOWLEDGE-BASED GEOGRAPHIC INFORMATION SYSTEM FOR SAFETY ANALYSIS AT RAIL-HIGHWAY GRADE CROSSINGS
• MODELING SCHEDULE DEVIATIONS OF BUSES USING AUTOMATIC VEHICLE-LOCATION DATA AND ARTIFICIAL NEURAL NETWORKS
• MODELING WASHINGTON STATE TRUCK FREIGHT FLOWS USING GIS-T: DATA COLLECTION AND DESIGN
• NEURAL NETWORK ESTIMATION OF WATERWAY LOCK SERVICE TIMES
• REAL-TIME DATA FUSION FOR ARTERIAL STREET INCIDENT DETECTION USING NEURAL NETWORKS
• SELECTION OF HIGHWAY DESIGN PARAMETERS IN THE PRESENCE OF UNCERTAINTY
• USE OF FUZZY RELATIONS TO MANAGE DECISIONS IN PRESERVING CIVIL INFRASTRUCTURE
• USING A KNOWLEDGE-BASED EXPERT SYSTEM AND FUZZY LOGIC FOR MINOR REHABILITATION PROJECTS IN OHIO