The paper presents a casual-probabilistic approach to the technical diagnosis in which the solution of the technical diagnostic problem is considered as a probabilistic inference on a special kind of Bayesian networks called Diagnostic Bayesian Networks. A mechanism of probabilistic inference and an algorithm for inference control are described. It is provided that a diagnostic problem represented by a singly connected Diagnostic Bayesian network can be decomposed to a sequence of subproblems with directed tree of multitree topology which are exactly solved in the sense of minimizing the average number of executed tests. The applications of the approach and future trends are briefly discussed.