scholarly journals Hybrid Fault Diagnosis of Bearings: Adaptive Fuzzy Orthonormal-ARX Robust Feedback Observer

2020 ◽  
Vol 10 (10) ◽  
pp. 3587 ◽  
Author(s):  
Farzin Piltan ◽  
Jong-Myon Kim
Keyword(s):  
Fuzzy Logic ◽  
Fault Diagnosis ◽  
Single Type ◽  
Support Vector ◽  
Signal Estimation ◽  
Adaptive Fuzzy ◽  
Reliability And Robustness ◽  
Non Stationary Signal ◽  
Fuzzy Logic Technique ◽  
Logic Structure

Rolling-element bearings (REBs) make up a class of non-linear rotating machines that can be applied in several activities. Conceding a bearing has complicated and uncertain behavior that exhibits substantial challenges to fault diagnosis. Thus, the offered anomaly-diagnosis algorithm, based on a fuzzy orthonormal-ARX adaptive fuzzy logic-structure feedback observer, is developed. A fuzzy orthonormal-ARX algorithm is presented for non-stationary signal modeling. Next, a robust, stable, reliable, and accurate observer is developed for signal estimation. Therefore, firstly, a classical feedback observer is implemented. To address the robustness drawback found in feedback observers, a multi-structure technique is developed. Furthermore, to generate signal estimation performance and reliability, the fuzzy logic technique is applied to the structure feedback observer. Also, to improve the stability, reliability, and robustness of the fuzzy orthonormal-ARX fuzzy logic-structure feedback observer, an adaptive algorithm is developed. After generating the residual signals, a support vector machine (SVM) is developed for the detection and classification of the bearing fault conditions. The effectiveness of the proposed procedure is validated using two different datasets for single-type fault diagnosis based on the Case Western Reverse University (CWRU) vibration dataset and multi-type fault diagnosis of bearing using the Smart Health Safety Environment (SHSE) Lab acoustic emission dataset. The proposed algorithm increases the classification accuracy from 86% in the SVM-based fuzzy orthonormal-ARX feedback observer to 97.5% in single-type fault and from 80% to 98.3% in the multi-type faults.

scholarly journals Mining of Completion Rate of Higher Education Based on Fuzzy Feature Selection Model and Machine Learning Techniques

2019 ◽  
Author(s):  
Tahseen A. Wotaifi
Keyword(s):  
Higher Education ◽  
Fuzzy Logic ◽  
Feature Selection ◽  
The United States ◽  
Ratio Method ◽  
Support Vector ◽  
Completion Rates ◽  
Academic Degree ◽  
Attribute Evaluation ◽  
Fuzzy Logic Technique

In the context of the great change in the labor market and the higher education sector, great attention is given to individuals with an academic degree or the so-called graduates class. However, each educational institution has a different approach towards students who wish to complete their university degree. This study aims at (1) identifying the most important factors that directly affect the completion, and (2) predicting the completion rates of students for university degrees according to the system of higher education in the United States. Unlike previous studies, this project contributes to the use of the fuzzy logic technique on three methods for feature selection, namely the Correlation Attribute Evaluation, Relief Attribute Evaluation, and Gain Ratio Method. Since these three methods give different weight to the same attribute, the fuzzy logic technique has been used to get one weight for the attribute. A great challenge faced throughout this study is the curse of dimensionality, because the college scorecard dataset launched by the US Department of Education contains approximately (8000) educational institutions and (1825) features. Applying the method used in this study to identify important features lead to their reduction to only (79). Accordingly, two models have been used to predict the completion rates of students for their university studies which are the Random Forest and the Support Vector Regression with a Mean Absolute Error (MAE) value of (0.068) and (0.097) respectively.

Circuit Fault Diagnosis Based on OEMD and SVDD Classifier of KFPCM Optimal Algorithm

2015 ◽  
Vol 738-739 ◽  
pp. 366-372
Author(s):  
Jian Feng Shan ◽  
Liang Wei Wang
Keyword(s):  
Fault Diagnosis ◽  
Hilbert Transform ◽  
Optimal Algorithm ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Hilbert Huang Transform ◽  
Mode Decomposition ◽  
Circuit Fault Diagnosis ◽  
The Hilbert Transform ◽  
Non Stationary Signal

Hilbert-Huang transform (HHT) has some problems such as insufficient characteristic, modal aliasing, illusive component in circuit fault feature extraction, a new method is proposed to obtain the transient characteristic which is especially suitable to process non-stationary signal. The method consists of orthogonal empirical mode decomposition (OEMD) and Hilbert transform. Use the OEMD algorithm to gain strict orthogonal intrinsic mode function (IMF) and obtain the characteristics such as time, amplitude and frequency after the Hilbert transform. Support vector data description (SVDD) is sensitive to noise and outliers. It needs to classify the data in advance, reduce noise and traversal data to the specific sample which has good similarity by using Kernelized Fuzzy Possibilistic C-Means clustering (KFPCM). Then put the sample into SVDD classifier for training and diagnosis. The results of experiments show that the SVDD improved by KFPCM has higher accuracy of fault diagnosis than original SVDD.

scholarly journals Mining of Completion Rate of Higher Education Based on Fuzzy Feature Selection Model and Machine Learning Techniques

2019 ◽  
Vol 8 (2S10) ◽  
pp. 393-400
Keyword(s):  
Higher Education ◽  
Fuzzy Logic ◽  
Feature Selection ◽  
The United States ◽  
Ratio Method ◽  
Support Vector ◽  
Completion Rates ◽  
Academic Degree ◽  
Attribute Evaluation ◽  
Fuzzy Logic Technique

In the context of the great change in the labor market and the higher education sector, great attention is given to individuals with an academic degree or the so-called graduates class. However, each educational institution has a different approach towards students who wish to complete their university degree. This study aims at (1) identifying the most important factors that directly affect the completion, and (2) predicting the completion rates of students for university degrees according to the system of higher education in the United States. Unlike previous studies, this project contributes to the use of the fuzzy logic technique on three methods for feature selection, namely the Correlation Attribute Evaluation, Relief Attribute Evaluation, and Gain Ratio Method. Since these three methods give different weight to the same attribute, the fuzzy logic technique has been used to get one weight for the attribute. A great challenge faced throughout this study is the curse of dimensionality, because the college scorecard dataset launched by the US Department of Education contains approximately (8000) educational institutions and (1825) features. Applying the method used in this study to identify important features lead to their reduction to only (79). Accordingly, two models have been used to predict the completion rates of students for their university studies which are the Random Forest and the Support Vector Regression with a Mean Absolute Error (MAE) value of (0.068) and (0.097) respectively.

scholarly journals FUZZY UNORDERED RULE USING GREEDY HILL CLIMBING FEATURE SELECTION METHOD: AN APPLICATION TO DIABETES CLASSIFICATION

2021 ◽  
Vol 20 (Number 3) ◽  
pp. 391-422
Author(s):  
Hayder Naser Khraibet Al-Behadili ◽  
Ku Ruhana Ku-Mahamud
Keyword(s):  
Fuzzy Logic ◽  
Feature Selection ◽  
Feature Selection Method ◽  
Classification Problem ◽  
Classification Criteria ◽  
Hill Climbing ◽  
Classification Model ◽  
Support Vector ◽  
Input Variables ◽  
Fuzzy Logic Technique

Diabetes classification is one of the most crucial applications of healthcare diagnosis. Even though various studies have been conducted in this application, the classification problem remains challenging. Fuzzy logic techniques have recently obtained impressive achievements in different application domains especially medical diagnosis. Fuzzy logic technique is not able to deal with data of a large number of input variables in constructing a classification model. In this research, a fuzzy logic technique using greedy hill climbing feature selection methods was proposed for the classification of diabetes. A dataset of 520 patients from the Hospital of Sylhet in Bangladesh was used to train and evaluate the proposed classifier. Six classification criteria were considered to authenticate the results of the proposed classifier. Comparative analysis proved the effectiveness of the proposed classifier against Naive Bayes, support vector machine, K-nearest neighbour, decision tree, and multilayer perceptron neural network classifiers. Results of the proposed classifier demonstrated the potential of fuzzy logic in analyzing diabetes patterns in all classification criteria.

scholarly journals Misalignment Fault Diagnosis for Wind Turbines Based on Information Fusion

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 243
Author(s):  
Yancai Xiao ◽  
Jinyu Xue ◽  
Long Zhang ◽  
Yujia Wang ◽  
Mengdi Li
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Frequency Domain ◽  
Least Square ◽  
Single Type ◽  
Support Vector ◽  
Posterior Probabilities ◽  
Time Frequency ◽  
Stator Current ◽  
Misalignment Fault

Most conventional wind turbine fault diagnosis techniques only use a single type of signal as fault feature and their performance could be limited to such signal characteristics. In this paper, multiple types of signals including vibration, temperature, and stator current are used simultaneously for wind turbine misalignment diagnosis. The model is constructed by integrated methods based on Dempster–Shafer (D–S) evidence theory. First, the time domain, frequency domain, and time–frequency domain features of the collected vibration, temperature, and stator current signal are respectively taken as the inputs of the least square support vector machine (LSSVM). Then, the LSSVM outputs the posterior probabilities of the normal, parallel misalignment, angular misalignment, and integrated misalignment of the transmission systems. The posterior probabilities are used as the basic probabilities of the evidence fusion, and the fault diagnosis is completed according to the D–S synthesis and decision rules. Considering the correlation between the inputs, the vibration and current feature vectors’ dimensionalities are reduced by t-distributed stochastic neighbor embedding (t-SNE), and the improved artificial bee colony algorithm is used to optimize the parameters of the LSSVM. The results of the simulation and experimental platform demonstrate the accuracy of the proposed model and its superiority compared with other models.

Helicopter main reduction planetary gear fault diagnosis method based on SVDD

2020 ◽  
Vol 64 (1-4) ◽  
pp. 137-145
Author(s):  
Yubin Xia ◽  
Dakai Liang ◽  
Guo Zheng ◽  
Jingling Wang ◽  
Jie Zeng
Keyword(s):  
Fault Diagnosis ◽  
Planetary Gear ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Vector Data ◽  
Energy Characteristics ◽  
Gear Fault ◽  
Channel Information ◽  
Diagnosis Method

Aiming at the irregularity of the fault characteristics of the helicopter main reducer planetary gear, a fault diagnosis method based on support vector data description (SVDD) is proposed. The working condition of the helicopter is complex and changeable, and the fault characteristics of the planetary gear also show irregularity with the change of working conditions. It is impossible to diagnose the fault by the regularity of a single fault feature; so a method of SVDD based on Gaussian kernel function is used. By connecting the energy characteristics and fault characteristics of the helicopter main reducer running state signal and performing vector quantization, the planetary gear of the helicopter main reducer is characterized, and simultaneously couple the multi-channel information, which can accurately characterize the operational state of the planetary gear’s state.

Sign in / Sign up

Export Citation Format

Share Document