{"title":"基于混合特征集和极限学习机分类器的摩托车声信号故障分类系统","authors":"T. Jayasree, R. Ananth","doi":"10.32604/sv.2020.08573","DOIUrl":null,"url":null,"abstract":": Vehicles generate dissimilar sound patterns under different working environments. These generated sound patterns signify the condition of the engines, which in turn is used for diagnosing various faults. In this paper, the sound signals produced by motorcycles are analyzed to locate various faults. The important attributes are extracted from the generated sound signals based on time, frequency and wavelet domains which clearly describe the statistical behavior of the signals. Further, various types of faults are classi fi ed using the Extreme Learning Machine (ELM) classi fi er from the extracted features. More-over, the improved classi fi cation performance is obtained by the combination of feature sets in different domains. The simulation results clearly demonstrate that the proposed hybrid feature set together with the ELM classi fi er gives more promising results with higher classi fi cation accuracy when compared with the other conventional methods.","PeriodicalId":49496,"journal":{"name":"Sound and Vibration","volume":"357 1","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Sound Signal Based Fault Classification System in Motorcycles Using Hybrid Feature Sets and Extreme Learning Machine Classifiers\",\"authors\":\"T. Jayasree, R. Ananth\",\"doi\":\"10.32604/sv.2020.08573\",\"DOIUrl\":null,\"url\":null,\"abstract\":\": Vehicles generate dissimilar sound patterns under different working environments. These generated sound patterns signify the condition of the engines, which in turn is used for diagnosing various faults. In this paper, the sound signals produced by motorcycles are analyzed to locate various faults. The important attributes are extracted from the generated sound signals based on time, frequency and wavelet domains which clearly describe the statistical behavior of the signals. Further, various types of faults are classi fi ed using the Extreme Learning Machine (ELM) classi fi er from the extracted features. More-over, the improved classi fi cation performance is obtained by the combination of feature sets in different domains. The simulation results clearly demonstrate that the proposed hybrid feature set together with the ELM classi fi er gives more promising results with higher classi fi cation accuracy when compared with the other conventional methods.\",\"PeriodicalId\":49496,\"journal\":{\"name\":\"Sound and Vibration\",\"volume\":\"357 1\",\"pages\":\"\"},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2020-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Sound and Vibration\",\"FirstCategoryId\":\"1089\",\"ListUrlMain\":\"https://doi.org/10.32604/sv.2020.08573\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ACOUSTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sound and Vibration","FirstCategoryId":"1089","ListUrlMain":"https://doi.org/10.32604/sv.2020.08573","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ACOUSTICS","Score":null,"Total":0}
Sound Signal Based Fault Classification System in Motorcycles Using Hybrid Feature Sets and Extreme Learning Machine Classifiers
: Vehicles generate dissimilar sound patterns under different working environments. These generated sound patterns signify the condition of the engines, which in turn is used for diagnosing various faults. In this paper, the sound signals produced by motorcycles are analyzed to locate various faults. The important attributes are extracted from the generated sound signals based on time, frequency and wavelet domains which clearly describe the statistical behavior of the signals. Further, various types of faults are classi fi ed using the Extreme Learning Machine (ELM) classi fi er from the extracted features. More-over, the improved classi fi cation performance is obtained by the combination of feature sets in different domains. The simulation results clearly demonstrate that the proposed hybrid feature set together with the ELM classi fi er gives more promising results with higher classi fi cation accuracy when compared with the other conventional methods.
期刊介绍:
Sound & Vibration is a journal intended for individuals with broad-based interests in noise and vibration, dynamic measurements, structural analysis, computer-aided engineering, machinery reliability, and dynamic testing. The journal strives to publish referred papers reflecting the interests of research and practical engineering on any aspects of sound and vibration. Of particular interest are papers that report analytical, numerical and experimental methods of more relevance to practical applications.
Papers are sought that contribute to the following general topics:
-broad-based interests in noise and vibration-
dynamic measurements-
structural analysis-
computer-aided engineering-
machinery reliability-
dynamic testing