971 KB43 KB199920252015Čudina, MirkoLipar, PrimožPrezelj, JurijŠteblaj, Peterštevilka:12letnik:61str. 698-708, SI 128ISSN:0039-2480COBISSID:14265627URN:URN:NBN:SI:doc-VXUWEQOMenZveza strojnih inženirjev in tehnikov Slovenije et al.Strojniški vestnikklasifikacija zvoka strojevKNS klasifikatorkoeficienti frekvenčnega kepstraVGP klasifikatorzvok strojevAutomatic recognition of machinery noise in the working environment|A necessity for suitable recognition of different machinery and equipment based on sound they generate is constantly present and will increase in the future . The main motivation of discrimination between different types of machinery sounds is to develop algorithms which can be used not only for end quality inspection, but for whole production line monitoring. Objective of our study is to recognize operation of individual machine in a production hall, where background noise level is high and is constantly changing. An exp erimental plan was designed and performed in order to confirm the hypothesis proposing that Automatic Speech Recognition algorithms can be applied for Automatic Machine Recognition. Design of the automatic machine recognition procedure used in our study wa s divided into three stages; Feature extraction, Training and Recognition (Classification). Additionally, a traditional MFCC (Mel - Frequency Cepstral Coefficient ) procedure was adjusted for machinery noise by using different filter compositions. Finally, tw o classifiers were compared, the k - NN classifier and the multivariate Gaussian distribution. Results of experiment show that machinery noise features (F requency C epstral C oefficient s) should be extracted by using linear filter compositions and processed wi th recognition algorithm based on the multivariate Gaussian distributionPostopki za avtomatizirano zaznavanje napak v končni kontroli izdelka, ali v samem proizvodnem procesu, so vse pogostejši. V ta namen so primerne metode, ki lahko na podlagi zvočnega signala, izdelka, stroja, naprave ali obdelovalnega postopka določijo njihova trenutna stanja. V tem delu so predstavljene metode za razpoznavanje različnih zvokov strojev, naprav in obdelovalnih postopkov, ki jih lahko uporabimo celo za nadzor celotnega proizvodnega procesa. Metode temeljijo na transformaciji biometrične zaznave govora, oziroma identifikacije govorcev, na identifikacijo različnih zvokov strojev, naprav in obdelovalnih postopkov z uporabo algoritmov za identifikacijo oseb na podlagi govornega signalaTEXTznanstveno časopisjejournalsSlovenian National E-content AggregatorNational and University Library of SloveniaUniverza v Ljubljani, Fakulteta za strojništvo