Pregled bibliografske jedinice broj: 1071491
Use of Artificial Neural Network for Estimation of Propeller Torque Values in a CODLAG Propulsion System
Use of Artificial Neural Network for Estimation of Propeller Torque Values in a CODLAG Propulsion System // Pomorski zbornik - Journal of Maritime and Transportation Sciences, 58 (2020), 1; 25-3/ doi:10.18048/2020.58.02. (međunarodna recenzija, prethodno priopćenje, ostalo)
CROSBI ID: 1071491 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Use of Artificial Neural Network for Estimation
of Propeller Torque Values in a CODLAG
Propulsion System
Autori
Sandi Baressi Šegota ; Daniel Štifanić ; Kazuhiro Ohkura ; Zlatan Car
Izvornik
Pomorski zbornik - Journal of Maritime and Transportation Sciences (0554-6397) 58
(2020), 1;
25-3/
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, prethodno priopćenje, ostalo
Ključne riječi
artificial neural network ; machine learning ; CODLAG ; propeller torque estimation ; 25 propulsion systems
Sažetak
An artificial neural network (ANN) approach is proposed to the problem of estimating the propeller torques of a frigate using combined diesel, electric and gas (CODLAG) propulsion system. The authors use a multilayer perceptron (MLP) feed-forward ANN trained with data from a dataset which describes the decay state coefficients as outputs and system parameters as inputs – with a goal of determining the propeller torques, removing the decay state coefficients and using the torque values of the starboard and port propellers as outputs. A total of 53760 ANNs are trained – 26880 for each of the propellers, with a total 8960 parameter combinations. The results are evaluated using mean absolute error (MAE) and coefficient of determination (R2). Best results for the starboard propeller are MAE of 2.68 [Nm], and MAE of 2.58 [Nm] for the port propeller with following ANN configurations respectively: 2 hidden layers with 32 neurons and identity activation and 3 hidden layers with 16, 32 and 16 neurons and identity activation function. Both configurations achieve R2 value higher than 0.99.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo, Strojarstvo, Temeljne tehničke znanosti
POVEZANOST RADA
Projekti:
Ostalo-CEI - 305.6019-20 - Use of regressive artificial intelligence (AI) and machine learning (ML) methods in modelling of COVID-19 spread (COVIDAi) (Car, Zlatan, Ostalo - CEI Extraordinary Call for Proposals 2020) ( CroRIS)
--KK.01.2.2.03.0004 - Centar kompetencija za pametne gradove (CEKOM) (Car, Zlatan; Slavić, Nataša; Vilke, Siniša) ( CroRIS)
NadSve-Sveučilište u Rijeci-uniri-tehnic-18-275-1447 - Razvoj inteligentnog ekspertnog sustava za online diagnostiku raka mokračnog mjehura (Car, Zlatan, NadSve - UNIRI potpore) ( CroRIS)
InoUstZnVO-CIII-HR-0108-10 - Concurrent Product and Technology Development - Teaching, Research and Implementation of Joint Programs Oriented in Production and Industrial Engineering (Car, Zlatan, InoUstZnVO - CEEPUS) ( CroRIS)
--KK.01.1.1.01.009 - Napredne metode i tehnologije u znanosti o podatcima i kooperativnim sustavima (DATACROSS) (Šmuc, Tomislav; Lončarić, Sven; Petrović, Ivan; Jokić, Andrej; Palunko, Ivana) ( CroRIS)
CIII-HR-0108
KK.01.2.2.03.0004
uniri-tehnic-18-275-1447
KK.01.1.1.01.0009 - Napredne metode i tehnologije u znanosti o podatcima i kooperativnim sustavima (EK )
Ustanove:
Tehnički fakultet, Rijeka
