کنفرانس مهندسی برق ایران

صفحه اصلی / سی و دومین کنفرانس بین المللی مهندسی برق

Gearbox Fault Detection Using Continuous Wavelet Transform and Vision Transformer (ViT)

نویسندگان :

Ali Asadian¹ Yassin Riyazi² Moosa Ayati³

1- دانشگاه تهران 2- دانشگاه تهران 3- دانشگاه تهران

کلمات کلیدی :

Gearbox fault detection،Imaging time-series،Multi-channel،Vision Transformers

چکیده :

Managing the substantial volume of data generated by gearbox operations and the inherent complexities underscores the strategic advantage of employing deep learning methods. This study addresses fault detection in the gearbox using a Vision Transformer (ViT), whose images were prepared by continuous wavelet transformation. The dataset from the Open Energy Data Initiative (OEDI) serves as the foundation for our analysis. Data recorded by four vibration sensors, situated in the time domain and various operating loads, transform into two-dimensional images which, after some manipulations, are fed into a ViT, allowing us to tackle the classification challenge with 'Healthy' and 'Damaged' classes. Remarkably, we achieved an outstanding accuracy of %99.1554, coupled with a reduction in the loss function to 0.040100. These results demonstrate the ViT's remarkable efficacy in detecting faults using images derived from signals recorded in the time domain.

لیست مقالات

لیست مقالات بایگانی شده

تولید پایگاه داده مصنوعی برای مقره های الکتریکی از روی داده‌های تصویری با استفاده از شبکه‌های مولد تخاصمی

امیرحسین جراره - ابولفضل منافی - سعید شمقدری

Learning-Based Routing Policy For Wireless Sensor Networks

‪Najim Halloum‬‏ - Yousef Darmani - Ali Ahmadi

An Optimal Investigation into A Preventive Maintenance Scheduling Scheme for Electric Power Transmission Networks

Seyed Sina Taheri Otaghsara - Masoud Asghari Gharakheili

Compare of Machine Learning and Deep Learning Approaches for Human Activity Recognition

Babak Moradi - Mohammad Aghapour - Afshin Shirbandi

Deep Learning-Based Imitation of Human Actions for Autonomous Pick-and-Place Tasks

Anoosheh Saadati - Mehdi Tale Masouleh - Ahmad Kalhor

Agglomerative Hierarchical Clustering Based on Q-learning for D2D Communication in Public Safety Communication Networks

Sahel Alipour - Mohammad Mansour Kesargheh - Abdulhamid Zahedi - Ghasem Mirjalily - Jamshid Abouei

An Iterative Approach to Enhance the Accuracy of TDOA-Based Localization by Averaging and Reducing Noise

Reza Bahrampour - Mohammad Hossein Madani - Hossein Bahramgiri

Towards Blockchain-based Remote Management Systems for Patients with Movement Disorders

Behnaz Behara - Mehdi Delrobaei

Spotting of a Particular Printed Word in Farsi Handwritten Forms Using Deep Learning

Mohammad jafar Gholami Kenari - Ehsanollah Kabir

A Lightweight Authentication Protocol For M2M Communication In IIoT Using Physical Unclonable Functions

Elaheh Kharghani - Saeed Aliakbari - Javad Bidad - Amir masoud Aminian moddares

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2