Deep Learning Approaches and Motor Current Signature Analysis in Detection of Broken Rotor Bar Faults

Özgür Aydın; Erhan Akın

Article Details

Deep Learning Approaches and Motor Current Signature Analysis in Detection of Broken Rotor Bar Faults

Authors:

Özgür Aydın | Erhan Akın

Publisher:

Bingol University

Main Topics:

Elektrik Makineleri ve Sürücüler

Journal:

Türk Doğa ve Fen Dergisi Vol.13 Issue 3, pp.1-7

Document Type:

Article

Publication Date:

9/2024

Document Language:

Turkish

Document ID (Org No.):

2001328010

pISSN:

2149-6366

Keywords:

Abstract:

 Induction motors are preferred in industrial applications due to their simple and robust structure, cost-effectiveness, self-starting capability, high efficiency, and reliability. However, faults like broken rotor bars occasionally encountered in these motors can lead to reduced performance and increased operating costs. Deep learning models are increasingly being used for the early detection of such faults. These models can recognize complex patterns in motor data to identify potential faults in advance, allowing for timely intervention, extending motor life, and ensuring production continuity. In this study, the diagnosis of broken rotor bars in induction motors was performed using four different deep learning models. Binary classification was conducted based on images obtained from current signals using a pre-existing dataset. The study achieved over 90 accuracy, thereby proving the effectiveness of deep learning models on induction motors.

 Induction motors are preferred in industrial applications due to their simple and robust structure, cost-effectiveness, self-starting capability, high efficiency, and reliability. However, faults like broken rotor bars occasionally encountered in these motors can lead to reduced performance and increased operating costs. Deep learning models are increasingly being used for the early detection of such faults. These models can recognize complex patterns in motor data to identify potential faults in advance, allowing for timely intervention, extending motor life, and ensuring production continuity. In this study, the diagnosis of broken rotor bars in induction motors was performed using four different deep learning models. Binary classification was conducted based on images obtained from current signals using a pre-existing dataset. The study achieved over 90 accuracy, thereby proving the effectiveness of deep learning models on induction motors.

 Induction motors are preferred in industrial applications due to their simple and robust structure, cost-effectiveness, self-starting capability, high efficiency, and reliability. However, faults like broken rotor bars occasionally encountered in these motors can lead to reduced performance and increased operating costs. Deep learning models are increasingly being used for the early detection of such faults. These models can recognize complex patterns in motor data to identify potential faults in advance, allowing for timely intervention, extending motor life, and ensuring production continuity. In this study, the diagnosis of broken rotor bars in induction motors was performed using four different deep learning models. Binary classification was conducted based on images obtained from current signals using a pre-existing dataset. The study achieved over 90 accuracy, thereby proving the effectiveness of deep learning models on induction motors.

 Asenkron motorlar, endüstriyel uygulamalarda sağladıkları basit ve sağlam yapı, maliyet etkinliği, kendiliğinden başlama kabiliyeti, yüksek verimlilik ve güvenilirlik gibi avantajlarla tercih edilir. Ancak, bu motorlarda zaman zaman karşılaşılan kırık rotor çubuğu gibi arızalar, performans düşüklüğüne ve işletme maliyetlerinin artmasına neden olabilir. Bu tür arızaların erken teşhisi için derin öğrenme modelleri giderek daha fazla kullanılmaktadır. Bu modeller, motor verilerinden karmaşık desenleri tanıyarak potansiyel arızaları önceden belirleyebilir, böylece zamanında müdahale ile motor ömrü uzatılabilir ve üretim sürekliliği sağlanabilir. Bu çalışma dört farklı derin öğrenme modeli kullanılarak asenkron motorlardaki kırık rotor çubuğu teşhisi gerçekleştirilmiştir. Hazır veri seti kullanılan çalışmada akım sinyalleri ile elde edilen görüntüler üzerinden ikili sınıflandırma yapılmıştır. Yapılan çalışma sonucunda 90 üzerinde başarım sağlanmıştır. Böylece derin öğrenme modellerinin asenkron motorlar üzerinde etkinliği kanıtlanmıştır.

Article Details

Deep Learning Approaches and Motor Current Signature Analysis in Detection of Broken Rotor Bar Faults

Authors:

Özgür Aydın | Erhan Akın

Publisher:

Bingol University

Main Topics:

Elektrik Makineleri ve Sürücüler

Journal:

Türk Doğa ve Fen Dergisi Vol.13 Issue 3, pp.1-7

Document Type:

Article

Publication Date:

9/2024

Document Language:

Turkish

Document ID (Org No.):

2001328010

pISSN:

2149-6366

Induction Motor

Fault Diagnosis

Broken Rotor Bar

Vision Transformer Model

Image ProcessingAsenkron Motor

Arıza Teşhisi

Kırık Rotor Çubuğu

Vision Transformer Model

Görüntü İşleme

Issues

Article Details

Authors: Özgür Aydın | Erhan Akın

Publisher: Bingol University

Main Topics: Elektrik Makineleri ve Sürücüler

Journal: Türk Doğa ve Fen Dergisi Vol.13 Issue 3, pp.1-7

Document Type: Article

Publication Date: 9/2024

Document Language: Turkish

Document ID (Org No.): 2001328010

pISSN: 2149-6366

Issues

Authors:

Özgür Aydın | Erhan Akın

Publisher:

Bingol University

Main Topics:

Elektrik Makineleri ve Sürücüler

Journal:

Türk Doğa ve Fen Dergisi Vol.13 Issue 3, pp.1-7

Document Type:

Article

Publication Date:

9/2024

Document Language:

Turkish

Document ID (Org No.):

2001328010

pISSN:

2149-6366