Prediction of bearing fault size by using model of adaptive neuro-fuzzy inference system

Abstract

Özetçe-Dönme işlemine sahip makinelerde, hayati öneme sahip olan rulmanların arıza durumlarının izlenmesi ve daha önceden hataların tespit edilmesi, prosesin aksamaması açısından büyük önem taşımaktadır. Bu çalışmada, rulman bileşenlerinden olan iç bilezik üzerine lazer ışını ile belirli boyutlarda yapay hatalar oluşturulmuş ve rulman-mil düzeneğinde titreşim sinyalleri elde edilmiştir. Çalışmada rulmanlarda meydana gelen arızaların boyutunu uyarlanabilir sinirsel-bulanık mantık çıkarım sistemi modelini kullanarak teşhis etmek amaçlanmıştır. Toplanan titreşim verilerinin gerçek zamanda özellikleri çıkarıldıktan sonra belirli ağırlıklarla çarpılmış ve oluşturulan sınıflandırma modeline giriş olarak verilmiştir. Lazer ile oluşturulan 0,15cm, 0,5cm, 0,9cm çaptaki iç bilezik hatalı rulmanların çıkarılan özelliklerinin hatanın boyutuna bağlı olarak farklı olduğu gözlemlenmiştir. Bu özellikler kullanılarak ANFIS sınıflandırma modeli geliştirilmiş ve rulmanın iç bileziğinde meydana gelen hatanın büyüklüğü, gerçek hata değerinden %2.40 bir farkla bulunmuştur. Daha sonra ANFIS çıkışında bulunan hata değerlerine uygulanan 0.1mm eşik değer ile hata bandı oluşturulmuş ve bütün tahmin değerlerinin bu hata bandı içerisinde çıktığı görülmüştür. Anahtar kelimeler-Arıza teşhis, ANFIS, rulman hataları, sınıflandırma Abstract-Condition monitoring of bearings faults which have vital importance in machines and detection of faults earlier have very big importance in terms of disruption of process.In this study, certain sizes artificial faults are generated by the laser beam on inner rings of bearing and vibration signals are obtained from these bearings in a shaftbearing setup. It is aimed to diagnose the size of the defects occurring in the bearings by using adaptive neuro-fuzzy inference system (ANFIS) model in the study. After extracting the real-time features of obtained vibration data, they are multiplied by the specific weight and they are given as input to the generated classification model. It has been observed difference of features extracted from of 0.15 cm, 0.5 cm, 0.9 cm diameter inner ring faulty bearings created by the laser depending on size of faults. ANFIS classification model is developed by using these features and the size of the faults occurring in these bearings were calculated with an actual error 2.40 %. Then a error band are created with 0.1mm threshold value and it is observed that all the predicted values are inside this error band.

Prediction of bearing failures by the analysis of the time series

“…As we can see, the use of ANNs for the prognosis is not new. In addition, we can find in the literature several papers dealing with the problem of bearings fault prediction [4], [16], [17], [18]. The proposed paper demonstrates that it is possible to use a new approach based on a simple architecture of a neural networks coupled with a technique based on the principle of the one-step and multi-step ahead prediction to obtain a reliable estimation of the RUL.…”

Design and Analysis of a Laminar Diffusion-Based Micromixer with Microfluidic Chip

“…Optimization with Fuzzy Logic. The claim that classical logic is insufficient to meet both right and wrong and neither right nor wrong at the same time because it is based on a two-valued system that is thought to see everything as right or wrong has led to the development of precious and fuzzy logic systems [36,37]. Fuzzy logic is the extraction of result values with the help of certain mathematical functions, depending on each rule that it will create, by processing the values obtained with specific algorithms using the result of experiences and data of people.…”

An Intelligent Approach for Bearing Fault Diagnosis: Combination of 1D-LBP and GRA

“…The experimental setup also consists of the signal amplifier, vibration sensors, data acquisition card, radial and axial load mechanism, and computer. Robust and artificial faulty bearings can be collected from this setup [23]- [25]. To create artificial defects, the bearing cages are divided into inner rings, outer rings, cages, and balls, as shown in Figure 2.…”