Multi-objective railway alignment optimization considering costs and environmental impacts

With increasing transportation requirements in mountainous regions, railways are encroaching ever more on environmentally-sensitive areas in those regions. Selecting an economical and eco-friendly railway alignment can effectively minimize negative impacts on mountain environments while also reducing costs. To this end, this paper formulates the alignment design problem as a multi-objective optimization model, which includes both economic and environmental objectives. Two new quantitative indexes for measuring environmental impacts are proposed to reflect the degree of vegetation destruction and soil erosion. A multi-objective optimization method based on the particle swarm optimization (PSO) algorithm is proposed for seeking non-dominated solutions. New update mechanisms for dealing with the multi-objective optimization problem are devised. A local repair algorithm based on a customized crossover operator is designed to save promising alignment alternatives during the search process. Two real-world cases are used to demonstrate the effectiveness of the proposed method. The results show that it can trade off the economic and environmental objectives and bypass all the pre-specified forbidden zones, thus providing designers a set of non-dominated alignment alternatives. (C) 2020 Elsevier B.V. All rights reserved.