collaborators

6 papers

cs.LG2025

A Comparative Analysis of Reinforcement Learning and Conventional Deep Learning Approaches for Bearing Fault Diagnosis

Efe Çakır, Patrick Dumond

Bearing faults in rotating machinery can lead to significant operational disruptions and maintenance costs. Modern methods for bearing fault diagnosis rely heavily on vibration ana…

cs.LG2025

Industrial Steel Slag Flow Data Loading Method for Deep Learning Applications

Mert Sehri, Ana Cardoso, Francisco de Assis Boldt +1

Steel casting processes are vulnerable to financial losses due to slag flow contamination, making accurate slag flow condition detection essential. This study introduces a novel cr…

cs.LG2025

Selective Embedding for Deep Learning

Mert Sehri, Zehui Hua, Francisco de Assis Boldt +1

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. Howeve…

cs.LG2025

Deep Learning Approach to Bearing and Induction Motor Fault Diagnosis via Data Fusion

Mert Sehri, Merve Ertagrin, Ozal Yildirim +2

Convolutional Neural Networks (CNNs) are used to evaluate accelerometer and microphone data for bearing and induction motor diagnosis. A Long Short-Term Memory (LSTM) recurrent neu…

cs.LG2025

Towards a Universal Vibration Analysis Dataset: A Framework for Transfer Learning in Predictive Maintenance and Structural Health Monitoring

Mert Sehri, Igor Varejão, Zehui Hua +5

ImageNet has become a reputable resource for transfer learning, allowing the development of efficient ML models with reduced training time and data requirements. However, vibration…

cs.LG2025

Advancing machine fault diagnosis: A detailed examination of convolutional neural networks

Govind Vashishtha, Sumika Chauhan, Mert Sehri +4

The growing complexity of machinery and the increasing demand for operational efficiency and safety have driven the development of advanced fault diagnosis techniques. Among these,…