لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
The 3rd International Conference on Electrical Machines and Drives
Novel preprocessing and data augmentation method for bearing fault diagnosis
نویسندگان :
Mohammad Mahdi Montasseri
1
Jawad Faiz
2
Farbod Parvin
3
Ahmad Kalhor
4
1- دانشگاه تهران
2- university of tehran
3- university of tehran
4- university of tehran
کلمات کلیدی :
bearing fault detection،signal processing،image enhancement،few-shot learning،deep learning
چکیده :
To avoid financial and life risks, early diagnose of bearing faults is particularly important, and this has made intelligent fault diagnosis popular. Intelligent fault diagnosis faces challenges such as the need for sufficient data and suitable performance for noisy data. This paper presents a preprocessing and data augmentation method to improve the performance of a few-shot learning method based on these two challenges. In this method first vibration signal is converted to two-dimensional images by means of mel spectrogram, then two image processing methods, namely, histogram equalization and gamma correction are applied. Finally, a data augmentation method based on gamma correction method is used. By using the Case Western Reserve University dataset, it is shown that the proposed method can improve the fault diagnosis process.
لیست مقالات
لیست مقالات بایگانی شده
Impact of Bridge and Linear De-Energized Tap Changer on Transformer Short-Circuit Impedance: An Analytical Approach
Mahsa Taghilou - Mojtaba Mirsalim
An Improved Active Feedforward Compensation Based on Model Predictive Control for Electrical Test Bench
Alireza Khalaj - Abolfazl Vahedi - Hossein Azizi-Moghaddam
Study of Flux Switching Machine Rotors from EMF Harmonic Components Point of View for Direct Drive wind power Application and Design of a new Topology with Double Rotor & Toroidal Coil
Rouhollah Rouhani - Alireza Rouhani
Novel Single-phase five-level current source CHB protection topology with SIC switches for induction motor
Amirhossein Ramezankhani - Amir Masoud Nouki - Farzad Bodaghi - Mohammadreza Arabshahi - Sobhan Mohammadian - Davood Arab Khaburi
Torque Profile Optimization of New Hybrid Reluctance Motor Using DOE Response Surface Methodology
Mohammad-Ali Mahmoudpour - Ali Harooni - Mojdeh Hossein Nejadi - Aghil Ghaheri - Ebrahim Afjei
Integrated Simulation of an E-Bike Powertrain and Vehicle Dynamics Using MATLAB/Simulink
ِDanial Gharibi - Mojtaba Mirsalim
Control of a Modular Drive for a Six-Phase Non-Sinusoidal PMSM with Asymmetric Open-End Winding Using the Reference Current Shaping Strategy
Abolfazl Halvaei Niasar
Modeling and simulation of a Novel Actuator for Medium-Voltage Vacuum Circuit Breakers Based on PMSM Servo Drive
Shahin Mahdiyounrad - Hamid Ashrafi - Hamed Mohajeri
Diagnosis of Broken Rotor Bars in Induction Machines Using a Current Signature-Based Adaptive Extended Kalman Filter
Saeed Hajnayeb - Seyyed Meysam Seyyed Barzegar - Mohammad Hoseintabar Marzebali - Javad Keighobadi
Multiphysics Analysis of the End winding Support System for a Medium Power Air-Cooled Turbo-generator
Behzad Bahrami Joo - Mojtaba Dehghani - Mohsen Nikfar
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.8.1