Adaptive neuro-fuzzy inference system for bearing fault detection in induction motors using temperature, current, vibration data

2009 ◽  
Author(s):  
Malik S. Yilmaz ◽  
Emine Ayaz
Keyword(s):  
Fault Detection ◽  
Fuzzy Inference System ◽  
Induction Motors ◽  
Fuzzy Inference ◽  
Inference System ◽  
Bearing Fault ◽  
Bearing Fault Detection ◽  
Vibration Data ◽  
Neuro Fuzzy

Machine Fault Detection Using Neuro-Fuzzy Inference System and Genetic Algorithms

2005 ◽  
Author(s):  
B. Samanta
Keyword(s):  
Genetic Algorithms ◽  
Fault Detection ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Inference System ◽  
Vibration Data ◽  
Neuro Fuzzy ◽  
Machine Fault ◽  
The Time Domain ◽  
Selection Of

A study is presented to show the performance of machine fault detection using adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithms (GAs), termed here as GA-ANFIS. The time domain vibration signals of a rotating machine with normal and defective gears are processed for feature extraction. The extracted features from original and preprocessed signals are used as inputs to GA-ANFIS for two class (normal or fault) recognition. The number and the parameters of membership functions used in ANFIS along with the features are selected using GAs maximizing the classification success. The results of fault detection are compared with GA based artificial neural network (ANN), termed here as GA-ANN. In GA-ANN, the number of hidden nodes and the selection of input features are optimized using GAs. For each trial, the GA-ANFIS and GA-ANN are trained with a subset of the experimental data for known machine conditions. The trained GA-ANFIS and GA-ANN are tested using the remaining set of data. The procedure is illustrated using the experimental vibration data of a gearbox. The results compare the effectiveness of both types of classifiers (ANFIS and ANN) with GA based selection of features and classifier parameters.

scholarly journals Proposed ANFIS Based Approach for Fault Tracking, Detection, Clearing and Rearrangement for Photovoltaic System

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2269
Author(s):  
Ahmed F. Bendary ◽  
Almoataz Y. Abdelaziz ◽  
Mohamed M. Ismail ◽  
Karar Mahmoud ◽  
Matti Lehtonen ◽  
...  
Keyword(s):  
Fault Detection ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Detection Methods ◽  
Photovoltaic Systems ◽  
Inference System ◽  
Photovoltaic Array ◽  
Neuro Fuzzy ◽  
Effective Manner ◽  
Simulation Results

In the last few decades, photovoltaics have contributed deeply to electric power networks due to their economic and technical benefits. Typically, photovoltaic systems are widely used and implemented in many fields like electric vehicles, homes, and satellites. One of the biggest problems that face the relatability and stability of the electrical power system is the loss of one of the photovoltaic modules. In other words, fault detection methods designed for photovoltaic systems are required to not only diagnose but also clear such undesirable faults to improve the reliability and efficiency of solar farms. Accordingly, the loss of any module leads to a decrease in the efficiency of the overall system. To avoid this issue, this paper proposes an optimum solution for fault finding, tracking, and clearing in an effective manner. Specifically, this proposed approach is done by developing one of the most promising techniques of artificial intelligence called the adaptive neuro-fuzzy inference system. The proposed fault detection approach is based on associating the actual measured values of current and voltage with respect to the trained historical values for this parameter while considering the ambient changes in conditions including irradiation and temperature. Two adaptive neuro-fuzzy inference system-based controllers are proposed: (1) the first one is utilized to detect the faulted string and (2) the other one is utilized for detecting the exact faulted group in the photovoltaic array. The utilized model was installed using a configuration of 4 × 4 photovoltaic arrays that are connected through several switches, besides four ammeters and four voltmeters. This study is implemented using MATLAB/Simulink and the simulation results are presented to show the validity of the proposed technique. The simulation results demonstrate the innovation of this study while proving the effective and high performance of the proposed adaptive neuro-fuzzy inference system-based approach in fault tracking, detection, clearing, and rearrangement for practical photovoltaic systems.

Roller Element Bearing Fault Size Estimation Using Adaptive Neuro-fuzzy Inference System (ANFIS)

2020 ◽  
Author(s):  
Sushant M. Patil ◽  
Ramchandra Ganapati Desavale ◽  
Surajkumar G Kumbhar
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Performance Indicator ◽  
Size Estimation ◽  
Vibration Level ◽  
Inference System ◽  
Bearing Fault ◽  
Neuro Fuzzy ◽  
Rotor Bearing ◽  
Bearing System

Abstract The vibration level is a function of the defects in the bearing. By identifying a change in vibration level, one can predict the dynamic behaviour and fault in the rotor- bearing system. An imminent bearing fault detection can reduce downtime or avoid the failure of rotating machinery. The condition monitoring or maintenance schedule can be set well if the diagnosis estimate bearing fault size accurately. In view of this, the Adaptive Neuro-Fuzzy Inference System (ANFIS) and dimension analysis (DA) was utilized to detect the bearing fault size. Several experiments were performed at different rotating speeds on the rotor-bearing system. Defects were created on bearing races artificially using electrode discharge machining (EDM) and the vibration responses are acquainted by accelerometer and Fast Fourier Techniques (FFT). With a 0.1 mm error band to fix minor bugs, a two-performance indicator evaluated the model accuracy. A comparison of the performance of models with experimental results and artificial neural network (ANN) are studied. The results showed that an ANFIS performs better over DA and ANN. This contributes to detecting bearing fault effectively and accuracy improvement in the estimation of the bearing fault size.

Sign in / Sign up

Export Citation Format

Share Document