The maintenance process has undergone several major developments that have led to proactive considerations and the transformation of the traditional "fail and fix" practice into the "predict and prevent" proactive maintenance methodology. The anticipation action, which characterizes this proactive maintenance strategy, is mainly based on monitoring, diagnosis, prognosis and decision-making modules. Oil monitoring is a key component of successful condition monitoring program. It can be used as a proactive tool to identify the wear modes of rubbing pars and diagnoses the faults in machinery. But diagnosis application relying on oil analysis technology must deal with uncertain knowledge and fuzzy input data. Besides other methods, Bayesian networks have been extensively applied to fault diagnosis with the advantages of uncertainty inference, however, in the area of oil monitoring, it is a new field. This paper develops an integrated Bayesian network based decision support system for maintenance of diesel.