Comparative study on ballistic impact detection in helicopter transmission shafts using NARX and LSTM models

Abstract

Vibration-based techniques are vital for online structural health monitoring (SHM) of rotating machines, enabling fault detection through feature analysis and threshold establishment. Rotating shafts typically exhibit non-linear dynamic behaviour, often due to misalignment or manufacturing imperfections leading to eccentricity. This non-linear behaviour is amplified after ballistic impact, leading to significant asymmetries and increased vibration loads. In this study, we develop an advanced vibration-based method to address the gap in diagnostic tools used to identify ballistic impact damage in helicopter transmission shafts. The proposed scheme employs a non-linear autoregressive model with exogenous inputs (NARX), evaluated against a long short-term memory (LSTM) model, to estimate acceleration signals from a two-sensor cluster. It then uses the estimation error arising from significant variations in signals acquired before and after ballistic impact to assess the structural integrity of the operating structure. The efficiency of the models is validated using experimental data obtained during ballistics testing. The results show that the proposed method effectively detects various types of impact damage, offering a promising tool for ballistic impact diagnosis in helicopter transmission shafts.