Fuel consumption minimization of transport aircraft using real-coded genetic algorithm

The issue of rising carbon dioxide emissions from aviation fuel consumption is increasingly crucial in terms of the Paris Agreement on climate change, which was adopted in 2015. The rapid growth of the global transport network has been affecting the environment adversely owing to the emission of greenhouse gases. Therefore, researchers are attempting to minimize aviation fuel consumption. This study presents a fuel consumption minimization problem in transport aircraft design. A real-coded genetic algorithm with direction-based crossover is employed to determine the optimum design for minimum fuel consumption. To mimic the aircraft fuel consumption issues, the proposed real-coded genetic algorithm employs the following three operators: ranking selection, direction-based crossover, and dynamic random mutation. Compared with earlier studies that used uniform crossover, the present study reduces the fuel consumption by applying real-coded genetic algorithm with a direction-based crossover operator. Comprehensive results show that the proposed real-coded genetic algorithm achieves remarkably faster convergence and improved search performance than the compared method. Direction-based crossover significantly enhances the fitness by guiding the crossover along a certain direction. In addition, it ensures a higher probability of locating the global optimum. Therefore, adopting such a technique can reduce the aircraft development cost.