• A.Naga Saikumar
• K. Venkata Rao
• CH. Lakshmi Kanth

For industrial systems to remain operationally efficient and minimize downtime, the diagnosis of mechanical problems is essential. Heuristic principles and manual inspection are frequently used in traditional fault detection techniques, which can be error-prone and time-consuming. New developments in machine learning (ML) provide viable substitutes by facilitating automatic and more precise fault diagnosis. The techniques for automatically identifying misalignment, unbalancing, looseness, and bearing wear in rotary machines are covered in this article. The defects in a rotating system are modelled using the finite element approach. In the steady-state operation, the modelled system then functions practically under various situations; the vibrational responses are computed numerically. To guarantee that equipment is operating well, regular monitoring is required. Condition monitoring is used to predict any problems by using several techniques mostly with vibration signals. The vibration signal technique is used in this study to predict defects in rotating machinery. A vibrometer is used to collect data from the rotating machine, which is then processed in Python using the Jupiter Notebook IDE. Based on the gathered data, predictive models like Support Vector Machine, Naive Bayes, and Logistic Regression are used to predict problems.

Condition Monitoring, Classification algorithms, Fault Diagnosis, Data Preprocessing, Predictive analysis.

"MACHINE LEARNING TECHNIQUES FOR THE IDENTIFICATION OF MACHINERY FAULTS THROUGH VIBRATION SIGNALS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.i384-i395, July-2024, Available :http://www.jetir.org/papers/JETIR2407837.pdf

"MACHINE LEARNING TECHNIQUES FOR THE IDENTIFICATION OF MACHINERY FAULTS THROUGH VIBRATION SIGNALS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. ppi384-i395, July-2024, Available at : http://www.jetir.org/papers/JETIR2407837.pdf