A Case Study Approach to Automatic Driving Train Using CBR with Differential Evolution

This paper presents a system applied in the automatic driving train using Case Based Reasoning (CBR) with Differential Evolution (DE). CBR was used to retrieve, reuse and revise experiences from real data during the journey. The DE was used to adapt the cases retrieved and optimize then considering multi-objective optimization. For this purpose, a train driving simulator used and the results compared the data of real train driving scenarios. Multi-objective optimization was used to reduce fuel consumption and also travel time. The results obtained concerning fuel consumption was entirely satisfactory because in some cases average savings of 45% in fuel consumption about the results obtained by human drivers. Adapting cases using the Differential Evolution approach led to a 5% gain in consumption over an adaptation of cases using Genetic Algorithm. It should also note that the time required for case adaptation was lower using Differential Evolution Algorithm than using Genetic Algorithm.