Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal
There are growing demands for condition-based monitoring of gearboxes, and techniques to improve the reliability, effectiveness and accuracy for fault diagnosis are considered valuable contributions. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/15/9/23903 |
| _version_ | 1818000514988638208 |
|---|---|
| author | Mariela Cerrada René Vinicio Sánchez Diego Cabrera Grover Zurita Chuan Li |
| author_facet | Mariela Cerrada René Vinicio Sánchez Diego Cabrera Grover Zurita Chuan Li |
| author_sort | Mariela Cerrada |
| collection | DOAJ |
| description | There are growing demands for condition-based monitoring of gearboxes, and techniques to improve the reliability, effectiveness and accuracy for fault diagnosis are considered valuable contributions. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach good performance in the diagnosis system. The main aim of this research is to propose a multi-stage feature selection mechanism for selecting the best set of condition parameters on the time, frequency and time-frequency domains, which are extracted from vibration signals for fault diagnosis purposes in gearboxes. The selection is based on genetic algorithms, proposing in each stage a new subset of the best features regarding the classifier performance in a supervised environment. The selected features are augmented at each stage and used as input for a neural network classifier in the next step, while a new subset of feature candidates is treated by the selection process. As a result, the inherent exploration and exploitation of the genetic algorithms for finding the best solutions of the selection problem are locally focused. The Sensors 2015, 15 23904 approach is tested on a dataset from a real test bed with several fault classes under different running conditions of load and velocity. The model performance for diagnosis is over 98%. |
| first_indexed | 2024-04-14T03:23:39Z |
| format | Article |
| id | doaj.art-5f53af634ccc47dd86c832e979c3ebcc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T03:23:39Z |
| publishDate | 2015-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5f53af634ccc47dd86c832e979c3ebcc2022-12-22T02:15:15ZengMDPI AGSensors1424-82202015-09-01159239032392610.3390/s150923903s150923903Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration SignalMariela Cerrada0René Vinicio Sánchez1Diego Cabrera2Grover Zurita3Chuan Li4Control Systems Department, Universidad de Los Andes, Mérida 5101, VenezuelaMechanical Engineering Department, Universidad Politécnica Salesiana, Cuenca 010150, EcuadorMechanical Engineering Department, Universidad Politécnica Salesiana, Cuenca 010150, EcuadorMechanical Engineering Department, Universidad Politécnica Salesiana, Cuenca 010150, EcuadorChongqing Key Laboratory of Manufacturing Equipment Mechanism Design and Control, Chongqing Technology and Business University, Chongqing 400067, ChinaThere are growing demands for condition-based monitoring of gearboxes, and techniques to improve the reliability, effectiveness and accuracy for fault diagnosis are considered valuable contributions. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach good performance in the diagnosis system. The main aim of this research is to propose a multi-stage feature selection mechanism for selecting the best set of condition parameters on the time, frequency and time-frequency domains, which are extracted from vibration signals for fault diagnosis purposes in gearboxes. The selection is based on genetic algorithms, proposing in each stage a new subset of the best features regarding the classifier performance in a supervised environment. The selected features are augmented at each stage and used as input for a neural network classifier in the next step, while a new subset of feature candidates is treated by the selection process. As a result, the inherent exploration and exploitation of the genetic algorithms for finding the best solutions of the selection problem are locally focused. The Sensors 2015, 15 23904 approach is tested on a dataset from a real test bed with several fault classes under different running conditions of load and velocity. The model performance for diagnosis is over 98%.http://www.mdpi.com/1424-8220/15/9/23903fault diagnosisgearboxvibration signalfeature selectiongenetic algorithmsneural networks |
| spellingShingle | Mariela Cerrada René Vinicio Sánchez Diego Cabrera Grover Zurita Chuan Li Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal Sensors fault diagnosis gearbox vibration signal feature selection genetic algorithms neural networks |
| title | Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal |
| title_full | Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal |
| title_fullStr | Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal |
| title_full_unstemmed | Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal |
| title_short | Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal |
| title_sort | multi stage feature selection by using genetic algorithms for fault diagnosis in gearboxes based on vibration signal |
| topic | fault diagnosis gearbox vibration signal feature selection genetic algorithms neural networks |
| url | http://www.mdpi.com/1424-8220/15/9/23903 |
| work_keys_str_mv | AT marielacerrada multistagefeatureselectionbyusinggeneticalgorithmsforfaultdiagnosisingearboxesbasedonvibrationsignal AT reneviniciosanchez multistagefeatureselectionbyusinggeneticalgorithmsforfaultdiagnosisingearboxesbasedonvibrationsignal AT diegocabrera multistagefeatureselectionbyusinggeneticalgorithmsforfaultdiagnosisingearboxesbasedonvibrationsignal AT groverzurita multistagefeatureselectionbyusinggeneticalgorithmsforfaultdiagnosisingearboxesbasedonvibrationsignal AT chuanli multistagefeatureselectionbyusinggeneticalgorithmsforfaultdiagnosisingearboxesbasedonvibrationsignal |