Estimation the Natural Frequencies of a Cracked Shaft Based on Finite Element Modeling and Artificial Neural Network

Abstract

The early detection of faults in rotating systems considers an integral approach that has received considerable attention from the industrial sector, as it contributes to preventing catastrophic failures in machines. In this research, the natural frequencies of a shaft, when it is healthy and when cracks with different depths are introduced, have been calculated. The deviation of the computed natural frequencies from the healthy ones is counted as a sign of the presence of an abnormality in the system. For this intention, the finite element analysis (FEA) method based on ANSYS software has been utilized to obtain the first five natural frequencies of the shaft when there is a crack of different severity at different positions. The results of the FEA are used for designing an artificial neural network (ANN) model that can be easily used to predict the first five natural frequencies of the shaft based on just the crack's position and depth. Finally, the predicted natural frequencies by the deigned ANN have been compared to their peers that were computed using the FEA method. The absolute error percentage has then been calculated and used to get an indication of how close the result of both techniques is. The recorded highest error percentage was 0.67%, which is quite small and referring to that the designed ANN can accurately predict the natural frequencies of rotating systems.

Harnessing a Better Future: Exploring AI and ML Applications in Renewable Energy

“…The optimization of project development procedures and the enhancement of the overall efficacy of investments in renewable energy are both positively impacted in this way. The utilization of artificial intelligence and machine learning technology enables the forecasting of maintenance needs in renewable energy infrastructure [127]- [129]. This is accomplished by analyzing data from sensors and monitoring equipment in order to identify potential equipment problems in advance.…”

An insight into the Application of AI in maritime and Logistics toward Sustainable Transportation

“…2) Predictive maintenance and condition monitoring Predictive maintenance and condition monitoring, which employ machine learning, are regarded as revolutionary in the marine industry. These methods are anticipated to significantly improve vessel dependability, operational efficiency, and cost-effectiveness [100], [101]. Machine learning empowers ship operators to detect and rectify potential equipment malfunctions proactively.…”

Vibration Signal Processing for Multirotor UAVs Fault Diagnosis: Filtering or Multiresolution Analysis?

“…In engineering and applied sciences, Finite Element Analysis (FEA) is of paramount importance, serving as a potent computational tool for simulating and analyzing complex structures and systems [66][67][68]. FEA has made a great contribution to UAV analysis due to their capability of structural analyzing, design, and topology optimization [38,69,70].…”