Rotating machinery is fundamental in industry, gearboxes especially. However, failures may occur in their transmission components due to regular usage over long periods of time, even when operations are not intense. To avoid such failures, Structural Health Monitoring (SHM) techniques for damage prediction and in-advance detection can be applied. In this regard, correlations between measured signal variations and damage can be inspected using Artificial Intelligence (AI), which demands large numbers of data for training. Since obtaining signal samples of damaged components experimentally is currently unviable for complex systems due to destructive test costs, model-based numerical approaches are to be explored to solve this problem. To address this issue, this work applied an innovative hybrid Finite Element Method (FEM)–analytical approach, reducing computational effort and increasing performance with respect to traditional FEM. With this methodology, a system can be simulated with accuracy and without geometrical simplifications for healthy and damaged cases. Indeed, considering different positions and dimensions of damages (e.g., cracks) on the tooth roots of gears can offer new ways of damage investigation. As a reference to validate healthy systems and damage cases in terms of eigenfrequencies, a back-to-back test rig was used. Numerical simulations were performed for different cases, resulting in vibrational spectra for systems with no damage, with damage, and with damage of different intensities. The vibration spectra were used as data to train an Artificial Neural Network (ANN) to predict the machine state by Condition Monitoring (CM) and Fault Diagnosis (FD). For predicting the health and the intensity of damage to a system, classification and multi-class classification methods were implemented, respectively. Both sets of classification results presented good prediction agreement.
Fault diagnosis of rotating machines by neural networks can be compromised in cases of imbalanced datasets, a common situation in the industry, where it might be necessary to create new data artificially. This subject, called data augmentation, is very recent and, for vibration signals, two approaches are found in the literature: the utilization of signal processing techniques in the time domain, and the creation of signal models by General Adversarial Network (GAN) from the existing signals. However, for this last one, many signal samples are necessary, which may prevent its use for this end. As an alternative, it is proposed a new vibration signal modelling method by using System Identification techniques at the frequency domain, where the trigger signal is used as model input and the vibration signal as output. By how it was structured, this method is only applicable in situations where only harmonic signal components are relevant to the diagnostics, case of many practical situations. For a first attempt of vibration signal modelling by System Identification, the results were very satisfactory, since the model responded with similarity to the collected signals in the frequency band of interest to the application. This work opens a new data augmentation research possibility for vibration signals of rotating machinery, a very relevant area and still little explored in the literature.