Identification and Classification of Imbalance Faults in Induction Motors Using Surrogate Models

Özgür Aydın; Erhan Akın

Makale detayları

Identification and Classification of Imbalance Faults in Induction Motors Using Surrogate Models

Yazarlar:

Özgür Aydın | Erhan Akın

Yayıncı:

Bingol University

Ana Başlıklar:

Bilgi Modelleme | Yönetim ve Ontolojiler | Elektrik Makineleri ve Sürücüler

Dergi:

Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.111-123

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001352633

pISSN:

2149-6366

Anahtar kelimeler:

Özet:

 Induction motors, with their robust structures, low maintenance costs, and high reliability, have a wide range of applications in the industry. However, these motors are susceptible to electrical and mechanical faults caused by environmental and operational conditions. Fault types include issues such as bearing problems, stator winding faults, and rotor bar breakages, with mechanical imbalance faults emerging as a critical issue that adversely affects motor performance. This study aims to compare the performance of surrogate models RBF and KRG with deep learning models RNN, GRU, LSTM for diagnosing imbalance faults in induction motors. For this purpose, the experimentally collected current Ia, Ib, Ic and vibration X, Y, Z signals were analyzed in the frequency domain, and the features obtained through FFT were used in the classification processes for three classes Healthy, DA_1, DA_2. According to the results, the RBF model exhibited the best performance with 97.78 accuracy and 97.64 precision, while the KRG model achieved a notable success with 93.89 accuracy and 93.71 precision. In contrast, the highest-performing deep learning models, RNN and LSTM, demonstrated lower performance with 87.22 accuracy and 87.23 precision. The RBF model outperformed the highest-accuracy deep learning model, RNN, by achieving a 12.11 improvement in accuracy and an 11.93 improvement in precision, proving to be a superior tool for diagnosing imbalance faults. Particularly, the RBF model achieved 100 accuracy in the DA_2 class, effectively distinguishing it from other classes due to its distinct features. These findings demonstrate that surrogate models offer an effective solution for diagnosing faults in induction motors by providing high accuracy and precision with limited data requirements and low computational cost.

 Induction motors, with their robust structures, low maintenance costs, and high reliability, have a wide range of applications in the industry. However, these motors are susceptible to electrical and mechanical faults caused by environmental and operational conditions. Fault types include issues such as bearing problems, stator winding faults, and rotor bar breakages, with mechanical imbalance faults emerging as a critical issue that adversely affects motor performance. This study aims to compare the performance of surrogate models RBF and KRG with deep learning models RNN, GRU, LSTM for diagnosing imbalance faults in induction motors. For this purpose, the experimentally collected current Ia, Ib, Ic and vibration X, Y, Z signals were analyzed in the frequency domain, and the features obtained through FFT were used in the classification processes for three classes Healthy, DA_1, DA_2. According to the results, the RBF model exhibited the best performance with 97.78 accuracy and 97.64 precision, while the KRG model achieved a notable success with 93.89 accuracy and 93.71 precision. In contrast, the highest-performing deep learning models, RNN and LSTM, demonstrated lower performance with 87.22 accuracy and 87.23 precision. The RBF model outperformed the highest-accuracy deep learning model, RNN, by achieving a 12.11 improvement in accuracy and an 11.93 improvement in precision, proving to be a superior tool for diagnosing imbalance faults. Particularly, the RBF model achieved 100 accuracy in the DA_2 class, effectively distinguishing it from other classes due to its distinct features. These findings demonstrate that surrogate models offer an effective solution for diagnosing faults in induction motors by providing high accuracy and precision with limited data requirements and low computational cost.

 Induction motors, with their robust structures, low maintenance costs, and high reliability, have a wide range of applications in the industry. However, these motors are susceptible to electrical and mechanical faults caused by environmental and operational conditions. Fault types include issues such as bearing problems, stator winding faults, and rotor bar breakages, with mechanical imbalance faults emerging as a critical issue that adversely affects motor performance. This study aims to compare the performance of surrogate models RBF and KRG with deep learning models RNN, GRU, LSTM for diagnosing imbalance faults in induction motors. For this purpose, the experimentally collected current Ia, Ib, Ic and vibration X, Y, Z signals were analyzed in the frequency domain, and the features obtained through FFT were used in the classification processes for three classes Healthy, DA_1, DA_2. According to the results, the RBF model exhibited the best performance with 97.78 accuracy and 97.64 precision, while the KRG model achieved a notable success with 93.89 accuracy and 93.71 precision. In contrast, the highest-performing deep learning models, RNN and LSTM, demonstrated lower performance with 87.22 accuracy and 87.23 precision. The RBF model outperformed the highest-accuracy deep learning model, RNN, by achieving a 12.11 improvement in accuracy and an 11.93 improvement in precision, proving to be a superior tool for diagnosing imbalance faults. Particularly, the RBF model achieved 100 accuracy in the DA_2 class, effectively distinguishing it from other classes due to its distinct features. These findings demonstrate that surrogate models offer an effective solution for diagnosing faults in induction motors by providing high accuracy and precision with limited data requirements and low computational cost.

 Asenkron motorlar, sağlam yapıları, düşük bakım maliyetleri ve yüksek güvenilirlikleri ile endüstride geniş bir kullanım alanına sahiptir. Ancak, bu motorlar çevresel ve operasyonel koşullardan kaynaklanan elektriksel ve mekanik arızalara maruz kalabilmektedir. Arıza türleri arasında rulman problemleri, stator sargı hataları ve rotor çubuğu kırılmaları gibi sorunlar yer almakta, özellikle mekanik dengesizlik arızaları motor performansını olumsuz etkileyen kritik bir sorun olarak öne çıkmaktadır. Bu çalışma, asenkron motorlarda dengesizlik arızalarının teşhis edilmesine yönelik yeni bir yaklaşım olan vekil modeller RBF ve KRG ile derin öğrenme modellerinin RNN, GRU, LSTM performansını karşılaştırmayı amaçlamaktadır. Bu amaçla, deneysel olarak toplanan akım Ia, Ib, Ic ve titreşim X, Y, Z sinyalleri, frekans alanında analiz edilmiş ve FFT ile elde edilen özellikler, üç sınıf Sağlıklı, DA_1, DA_2 için sınıflandırma süreçlerinde kullanılmıştır. Sonuçlara göre, RBF modeli, 97.78 doğruluk ve 97.64 keskinlik oranı ile en iyi performansı sergilemiş, KRG modeli ise 93.89 doğruluk ve 93.71 keskinlik oranı ile dikkate değer bir başarı göstermiştir. Buna karşılık, derin öğrenme modellerinden en yüksek doğruluk oranına sahip olan RNN ve LSTM 87.22 doğruluk ve 87.23 keskinlik oranı ile daha düşük bir performans göstermiştir. RBF modeli, en yüksek doğruluklu derin öğrenme modeli olan RNNe göre doğruluk oranında 12.11, keskinlik oranında ise 11.93lük bir artış sağlamış, bu da dengesizlik arızalarının teşhisinde üstün bir araç olduğunu kanıtlamıştır. Özellikle DA_2 sınıfında 100 doğruluk oranına ulaşarak, belirgin özellikleri sayesinde diğer sınıflardan ayrışmıştır. Bu bulgular, vekil modellerin sınırlı veri gereksinimi ve düşük hesaplama maliyetiyle birlikte yüksek doğruluk ve keskinlik oranları sunarak, asenkron motor arıza teşhisinde etkili bir çözüm sunduğunu göstermektedir.

Makale detayları

Identification and Classification of Imbalance Faults in Induction Motors Using Surrogate Models

Yazarlar:

Özgür Aydın | Erhan Akın

Yayıncı:

Bingol University

Ana Başlıklar:

Bilgi Modelleme | Yönetim ve Ontolojiler | Elektrik Makineleri ve Sürücüler

Dergi:

Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.111-123

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001352633

pISSN:

2149-6366

Asynchronous Motor Fault Diagnosis

Surrogate Model

Imbalance Faults

Vibration Analysis

Multi-Model ClassificationAsenkron Motor Arıza Teşhisi

Vekil Model

Dengesizlik Arızası

Titreşim Analizi

Çoklu Model Sınıflandırma

Sayı

Makale detayları

Yazarlar: Özgür Aydın | Erhan Akın

Yayıncı: Bingol University

Ana Başlıklar: Bilgi Modelleme | Yönetim ve Ontolojiler | Elektrik Makineleri ve Sürücüler

Dergi: Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.111-123

Belge Tipi: Makale

Yayın Tarihi: 6/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001352633

pISSN: 2149-6366

Sayı

Yazarlar:

Özgür Aydın | Erhan Akın

Yayıncı:

Bingol University

Ana Başlıklar:

Bilgi Modelleme | Yönetim ve Ontolojiler | Elektrik Makineleri ve Sürücüler

Dergi:

Türk Doğa ve Fen Dergisi Vol.14 Issue 2, pp.111-123

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001352633

pISSN:

2149-6366