• Prerna Nikhar
• Dhanashree Gadge
• Yashsvi Chavan
• Roshani Welekar
• Prajyoti Ingle

Gears are fundamental components in various mechanical systems, facilitating the transfer of motion and power. However, due to continuous operation and environmental factors, gears are prone to various types of faults, including tooth breakage, wear, and misalignment, which can lead to catastrophic failures if left undetected. Early detection of these faults is crucial for ensuring operational efficiency and preventing costly downtime. Traditional methods of fault detection often rely on manual inspection or rule-based algorithms, which can be time-consuming and may lack robustness. In this paper, we propose an Automatic Faulty Gear Identification System (AFGIS) utilizing deep learning techniques for accurate and automated identification of gear faults. We present a comprehensive analysis of different types of gear faults and their manifestations in vibration signals. The proposed system employs convolutional neural networks (CNNs) to automatically learn discriminative features from vibration data, enabling the detection of various types of gear faults. Experimental results demonstrate the effectiveness of the AFGIS in accurately identifying gear faults and distinguishing between different fault types, thereby facilitating proactive maintenance and enhancing the reliability of mechanical systems.

Data Preprocessing, Convolutional Neural Networks, Automatic, Identification, Misalignment, Fault, Gear.

"Automatic Faulty Gear Identification System and its Types Using Deep Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.p446-p449, April-2024, Available :http://www.jetir.org/papers/JETIR2404G56.pdf

"Automatic Faulty Gear Identification System and its Types Using Deep Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppp446-p449, April-2024, Available at : http://www.jetir.org/papers/JETIR2404G56.pdf