Razvoj neuronskog modela rada disk kočnice
Development of neural network model of disc brake operation
dc.creator | Ćirović, Velimir | |
dc.creator | Aleksendrić, Dragan | |
dc.date.accessioned | 2022-09-19T16:25:13Z | |
dc.date.available | 2022-09-19T16:25:13Z | |
dc.date.issued | 2010 | |
dc.identifier.issn | 1451-2092 | |
dc.identifier.uri | https://machinery.mas.bg.ac.rs/handle/123456789/1025 | |
dc.description.abstract | Kvalitet veštačkih neuronskih modela pretežno zavisi od pravilnog izbora arhitekture veštačke neuronske mreže, odnosno algoritma učenja, funkcije prenosa, opsega i raspodele podataka korišćenih za obuku, validaciju i testiranje. Osnovni cilj ovog rada se odnosi na istraživanje kako arhitekture veštačkih neuronskih mreža utiču na uspešnost predviđanja tj. sposobnost generalizacije mreža za isti set podataka za obuku i testiranje. Kompleksni postupak razvoja veštačkog neuronskog modela je demonstriran na primeru disk kočnice. Modeliran je uticaj radnih uslova disk kočnice (pritisak aktiviranja, početna brzina i temperatura) na njene maksimalne performanse kao i performanse opadanja i obnavljanja efikasnosti. Veštački neuronski model je razvijan kroz istraživanje na koji način sinergija različitih parametara mreže, poput algoritma učenja, funkcije prenosa i broja neurona u skrivenim slojevima, utiče na sposobnosti neuronskog modela da predvidi performanse disk kočnice. U ovom radu je pokazano da kompleksne nelinearne zavisnosti između posmatranih ulaznih i izlaznih parametara mogu biti modelirane odgovarajućom analizom i podešavanjem parametara veštačke neuronske mreže. | sr |
dc.description.abstract | The quality of artificial neural network models mostly depends on a proper setting of neural network architecture i.e. learning algorithm, transfer functions, range and distribution of data used for training, validation, and testing, etc. The goal of this paper is related to the investigation on how artificial neural network architectures influence the network's generalization performance based on the same input/output parameters. The complex procedure of an artificial neural network model development has been demonstrated related to the disc brake performance. The influence of disc brake operation conditions (application pressure, initial speed, and temperature) has been modeled related to the disc brake cold, fade, and recovery performance. The artificial neural network model has been developed through investigation of how the synergy of different network's parameters, such as learning algorithm, transfer functions, the number of neurons in the hidden layers, affect the neural model abilities to predict the disc brake performance. It was shown in this paper that complex non-linear interrelations between the disc brake input/output variables can be modeled by proper analysis and setting of artificial neural network parameters. . | en |
dc.publisher | Univerzitet u Beogradu - Mašinski fakultet, Beograd | |
dc.relation | info:eu-repo/grantAgreement/MESTD/MPN2006-2010/14006/RS// | |
dc.relation | info:eu-repo/grantAgreement/MESTD/MPN2006-2010/15012/RS// | |
dc.rights | openAccess | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
dc.source | FME Transactions | |
dc.subject | performance | en |
dc.subject | neural modeling | en |
dc.subject | disc brake | en |
dc.subject | artificial neural network | en |
dc.title | Razvoj neuronskog modela rada disk kočnice | sr |
dc.title | Development of neural network model of disc brake operation | en |
dc.type | article | |
dc.rights.license | BY | |
dc.citation.epage | 38 | |
dc.citation.issue | 1 | |
dc.citation.other | 38(1): 29-38 | |
dc.citation.rank | M51 | |
dc.citation.spage | 29 | |
dc.citation.volume | 38 | |
dc.identifier.fulltext | http://machinery.mas.bg.ac.rs/bitstream/id/12/1022.pdf | |
dc.identifier.rcub | https://hdl.handle.net/21.15107/rcub_machinery_1025 | |
dc.identifier.scopus | 2-s2.0-79959954697 | |
dc.type.version | publishedVersion |