[211] Nature of errors in machinery diagnostics

A Kostyukov, A Kostyukov and S Boichenko

Dynamics SPC, 108 Rabinovicha Str Omsk 644043, Russian Federation

A reliability theory has been developing for almost 70 years and, all the time, scientists, engineers and practitioners attempt to point out instances of machine failure in order to prevent breakdown. Since that time, many types of instrument have been developed and all of them – vibration pens, portable analysers, protection and condition monitoring systems – have been pursuing that goal. Today, some artificial intelligence (AI) systems utilise the statistical analysis of big data to solve this problem; however, their developers meet either poor and insufficient data or incorrect data that are either almost or completely unrelated to the equipment’s lifespan. Therefore, it is inevitable that those AI systems assess the probability of failure seldom more than 50%. To be able to provide a precise diagnosis of machinery health, the algorithms of AI should include the physics-based rules of degradation. Hence, three topics will be considered in this paper: what the nature of errors is concerning the recognition of the degradation process; what a failure is; and what it means to recognise a defect.