Reliability and types of diagnosis in the process of diesel engine operation

The article presents complexity of the problem concerning development of diagnosis with defined reliability by a diagnosing system (SDG) on technical condition of marine combustion engines, especially main engines. It was shown that development of the final diagnosis, the so-called initial operation diagnosis, on the operational usability (fDG on PEx) of a main engine in particular, is not possible without prior development of reliable diagnoses such as: diagnosis on correctness of diagnostic signals, diagnosis on correctness of values of the measured diagnostic parameters of an engine (DG on pWM), diagnosis on technical condition of an engine (DG on ST) and initial diagnosis on operational usability of an engine (wDG on PEx), the so-called initial operation diagnosis. Difficulties in development of the diagnoses were emphasized herein due to the fact that the process of acquisition of information needed to develop diagnoses with certain reliability or accuracy is a two-dimensional stochastic process with components: B(t) – being considered during operation (use) of SDG (at so-called long time - quasistatic) and C(ʋ) – being considered while measuring diagnostic parameters and diagnostic inference (at so-called short time - dynamic). The need to determine reliability or accuracy rate of each diagnosis in the form of conditional probability P(S/K) was also indicated, where S – technical state of the engine and K – vector of values of diagnostic parameters reflecting state S. Diagnostic status of marine engine as a diagnosed system (SDN) was characterized in general, on the example of an engine operation process with regards to input (X), output (Y), constant (C) and interference (Z) values. Also there was explained how to understand the terms: diagnostic test, signal inference, measurement inference, structure inference and operation inference, and how inductive inference can be used to verify, for example, the hypothesis H on engine state S when vector K of values of engine diagnostic parameters is observed