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.

Machine Fault Detection Using Genetic Programming

2005 ◽  
Author(s):  
B. Samanta
Keyword(s):  
Fault Detection ◽  
Genetic Programming ◽  
Vibration Data ◽  
Rotating Machine ◽  
Fault Recognition ◽  
Machine Fault ◽  
Artificial Neural Network Ann ◽  
Monitoring And Diagnostics ◽  
The Time Domain ◽  
Selection Of

Applications of genetic programming (GP) include many areas. However applications of GP in the area of machine condition monitoring and diagnostics is very recent and yet to be fully exploited. In this paper, a study is presented to show the performance of machine fault detection using GP. 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 GP for two class (normal or fault) recognition. The number of features and the features are automatically selected in GP maximizing the classification success. The results of fault detection are compared with genetic algorithm (GA) based artificial neural network (ANN)- termed here as GA-ANN. The number of hidden nodes in the ANN and the selection of input features are optimized using GAs. Two different normalization schemes for the features have been used. For each trial, the GP and GA-ANN are trained with a subset of the experimental data for known machine conditions. The trained GP 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 with GP and GA based selection of features.

scholarly journals Parsimonious Network Based on a Fuzzy Inference System (PANFIS) for Time Series Feature Prediction of Low Speed Slew Bearing Prognosis

2018 ◽  
Vol 8 (12) ◽  
pp. 2656 ◽  
Author(s):  
Wahyu Caesarendra ◽  
Mahardhika Pratama ◽  
Buyung Kosasih ◽  
Tegoeh Tjahjowidodo ◽  
Adam Glowacz
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Predictive Analytics ◽  
Critical Role ◽  
Inference System ◽  
Low Speed ◽  
Vibration Data ◽  
Machine Failure ◽  
The Time Domain ◽  
Parsimonious Network

In recent years, the utilization of rotating parts, e.g., bearings and gears, has been continuously supporting the manufacturing line to produce a consistent output quality. Due to their critical role, the breakdown of these components might significantly impact the production rate. Prognosis, which is an approach that predicts the machine failure, has attracted significant interest in the last few decades. In this paper, the prognostic approaches are described briefly and advanced predictive analytics, namely a parsimonious network based on a fuzzy inference system (PANFIS), is proposed and tested for low speed slew bearing data. PANFIS differs itself from conventional prognostic approaches, supporting online lifelong prognostics without the requirement of a retraining or reconfiguration phase. The PANFIS method is applied to normal-to-failure bearing vibration data collected for 139 days to predict the time-domain features of vibration slew bearing signals. The performance of the proposed method is compared to some established methods, such as ANFIS, eTS, and Simp_eTS. From the results, it is suggested that PANFIS offers an outstanding performance compared to those methods.

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.

Sign in / Sign up

Export Citation Format

Share Document