Effect of Pre-processing on Using ANN and ANFIS
| Main Author: | Moustafa Hassan, Mohamed A. |
|---|---|
| Format: | Proceeding Journal |
| Bahasa: | eng |
| Terbitan: |
FRUCT Oy
, 2020
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/4007434 |
Daftar Isi:
- Rotating machines are widely utilized in industrial lifecycle, since it represents a vital element in industrial processes. Therefore, quick detection of faults of rotating machines is necessary to sidestep the forced stopping for frequent maintenance in industrial progressions. Several condition monitoring and detecting procedures are used to diagnose the rotating machinery faults based on currents values, vibration signature analysis, temperature monitoring, noise signature analysis, lubricant signature analysis using Artificial Intelligence (AI) techniques. Many AI methods are in use for detection of faults of rotating machines. For instance, Fuzzy Inference System (FIS); Artificial Neural Networks (ANNs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are among AI techniques are advanced technologically for classifying and detection various rotating machinery faults. This research work describes a comprehensive methods to some extent for detecting and classification of rotating machines faults using two methods of artificial intelligence which are ANN and ANFIS. This study is implemented offline in MATLAB environment based on data preprocessing before applying ANN or ANFIS. The obtained data of rolling element were classified into different main conditions. The obtained data after preprocessing were imported to ANNs and ANFIS models. These studies work presents a comparison between the diagnosing based on ANNs and ANFIS. The input data were preprocessed before entering to ANNs and ANFIS models by using some techniques: the normalized data in range (0-1), the frequency domain analysis via discrete wavelet transform, the time domain features, and finally the Auto Regressive (AR) model. The accomplished outcomes of these preprocessing techniques give high accuracy results in faults detection and classification issues. The accomplished outcomes are encouraging and promising in the field of diagnosis of machinery faults.