Physics-guided neural networks applied in rotor unbalance problems

Rotary systems are extremely important for the development of industrial production due to the large amount of work performed by these machines. However, rotating machines are prone to unbalance faults, which can reduce efficiency and, in the worst-case scenario, lead to catastrophic failure. Since artificial neural networks (ANNs) are very efficient at recognizing complex patterns, they are a useful tool to help diagnose and prevent rotor unbalance faults. Physics-Guided Machine Learning (PGML) is a class of machine learning algorithm that uses physical laws in its structure. In this paper, a method for unbalance fault identification using PGML is proposed, more specifically ANNs as machine learning—Physics-Guided Neural Networks (PGNN) is used. The first step adopts a standard ANN to locate the nodal position of the experimental fault. Afterwards, the PGNN is performed to quantify the unbalance magnitude and phase angle. Also, a comparison between the performance of the standard ANN and PGNN is accomplished. As input, the networks use simulation data of a rotor supported by hydrodynamic bearings modeled through the finite element method (FEM) and Reynolds’ equation. The results showed that the PGNN has smaller errors and better performance than the standard ANN. In addition, a small increase in the number of neurons improves the results of both networks.