The presented article shows a method for finding monitored parameters for creating a diagnostic system for autonomous power sources based on spark ignition engines and diesel engines. The classification of structures of autonomous power sources based on internal combustion engines has been carried out. The analysis of the design features of the most common back-up power sources on the market based on internal combustion engines (ICE) indicates the widespread use of generators with a synchronous alternator. The analysis of the design features of autonomous power supplies has made it possible to develop logical models for different designs. The influence of the occurrence of a faulty state of each element on other elements of the systems is analyzed, and the results of the analysis are summarized in tables. An informative Claude Chenon criterion is proposed for finding the optimal number of diagnostic parameters among an infinite number of possible combinations of physical parameters that characterize the system. When solving the problem, a hypothesis was proposed about the equiprobability of cases of exit from the working state of each of the elements of the system. The use of Claude Chenon allows you to find the parts that make up the generators, which with maximum efficiency reduce the degree of uncertainty in the system. After determining the residual entropy, the parts of the system are selected, the state of which should be monitored by the diagnostic system. For such parts of the system, diagnostic parameters are found and methods for obtaining them are indicated.