development of an aircraft failure prediction model using an adaptive neuro-fuzzy inference system

Ensuring safety within the aviation domain is of paramount importance due to the severe consequences associated with compromised safety, including loss of lives and substantial financial losses that are often irrecoverable. therefore, the pursuit of maximum safety stands as a central objective within the realm of aviation technology advancements. this research endeavors to introduce an innovative approach by employing an adaptive neuro-fuzzy inference system (anfis)-based classifier to assess the potential fault risk inherent in aircraft operations. the development of this classifier draws on a comprehensive dataset encompassing five distinct categories: structural components, electrical systems, avionics, motor systems, and historical incident statistics related to aircraft. the core outcome of this intelligent classifier is the quantification of a risk factor corresponding to each aircraft. this risk factor evaluation holds the potential to serve as a pivotal tool for identifying aircraft eligible for comprehensive overhauls, thereby preemptively addressing defects and averting potential accidents. the empirical findings of this study underscore the efficacy of the anfis methodology, showcasing its adeptness in processing a diverse array of input parameters and corresponding outcomes spanning various facets and classifications within the aviation industry. this, in turn, bolsters its efficacy in accurately prognosticating the likelihood of aircraft failure, thus enhancing overall safety measures.