Modern trains are capable of monitoring health status in real time and infer behaviour of various systems. This trend will grow with advancements of machine learning those will produce feedback for continuously improving the prediction models. Despite reduced physical connectivity of human with locomotive systems, human interference will be required for critical decision-making. Human implicit learning involves the largely unconscious learning of dynamic statistical patterns and features, which leads to the development of tacit knowledge1. Pirsig2 argued that “each machine has its own, unique personality which probably could be defined as the intuitive sum total of everything you know and feel about it”. Theses suggest that humans employ an intuitive cognition ability that leads to developing implicit knowledge and interactions with machines. In this study, we focus on signifying the implicit knowledge in locomotive operation context and seek ways to facilitate effective decision-making