Prediction of automotive friction material characteristics using artificial neural networks-cold performance
Само за регистроване кориснике
2006
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
In this study, an artificial neural network technique was used to predict the cold performance of the automotive friction material. Cold performance was predicted for two cases: (i) before and (ii) after fading and recovery tests. Predictions were related to the brake factor C values versus 26 input parameters. The input parameters are defined by the friction material formulation (18 parameters), manufacturing conditions (5 parameters), and testing conditions (3 parameters). For these predictions, the five types of the friction materials were produced and tested. The quality of prediction has been evaluated by comparison of the real results obtained during testing on the single-end full-scale inertia dynamometer and predicted ones. The 15 different architectures of the artificial neural networks have been investigated. The five training algorithms have been employed for the artificial neural networks training.
Кључне речи:
testing / manufacturing / friction characteristics / formulation / cold performance / artificial neural networkИзвор:
Wear, 2006, 261, 3-4, 269-282Издавач:
- Elsevier Science Sa, Lausanne
DOI: 10.1016/j.wear.2005.10.006
ISSN: 0043-1648
WoS: 000239678300006
Scopus: 2-s2.0-33745973888
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Aleksendrić, Dragan AU - Duboka, Čedomir PY - 2006 UR - https://machinery.mas.bg.ac.rs/handle/123456789/616 AB - In this study, an artificial neural network technique was used to predict the cold performance of the automotive friction material. Cold performance was predicted for two cases: (i) before and (ii) after fading and recovery tests. Predictions were related to the brake factor C values versus 26 input parameters. The input parameters are defined by the friction material formulation (18 parameters), manufacturing conditions (5 parameters), and testing conditions (3 parameters). For these predictions, the five types of the friction materials were produced and tested. The quality of prediction has been evaluated by comparison of the real results obtained during testing on the single-end full-scale inertia dynamometer and predicted ones. The 15 different architectures of the artificial neural networks have been investigated. The five training algorithms have been employed for the artificial neural networks training. PB - Elsevier Science Sa, Lausanne T2 - Wear T1 - Prediction of automotive friction material characteristics using artificial neural networks-cold performance EP - 282 IS - 3-4 SP - 269 VL - 261 DO - 10.1016/j.wear.2005.10.006 ER -
@article{ author = "Aleksendrić, Dragan and Duboka, Čedomir", year = "2006", abstract = "In this study, an artificial neural network technique was used to predict the cold performance of the automotive friction material. Cold performance was predicted for two cases: (i) before and (ii) after fading and recovery tests. Predictions were related to the brake factor C values versus 26 input parameters. The input parameters are defined by the friction material formulation (18 parameters), manufacturing conditions (5 parameters), and testing conditions (3 parameters). For these predictions, the five types of the friction materials were produced and tested. The quality of prediction has been evaluated by comparison of the real results obtained during testing on the single-end full-scale inertia dynamometer and predicted ones. The 15 different architectures of the artificial neural networks have been investigated. The five training algorithms have been employed for the artificial neural networks training.", publisher = "Elsevier Science Sa, Lausanne", journal = "Wear", title = "Prediction of automotive friction material characteristics using artificial neural networks-cold performance", pages = "282-269", number = "3-4", volume = "261", doi = "10.1016/j.wear.2005.10.006" }
Aleksendrić, D.,& Duboka, Č.. (2006). Prediction of automotive friction material characteristics using artificial neural networks-cold performance. in Wear Elsevier Science Sa, Lausanne., 261(3-4), 269-282. https://doi.org/10.1016/j.wear.2005.10.006
Aleksendrić D, Duboka Č. Prediction of automotive friction material characteristics using artificial neural networks-cold performance. in Wear. 2006;261(3-4):269-282. doi:10.1016/j.wear.2005.10.006 .
Aleksendrić, Dragan, Duboka, Čedomir, "Prediction of automotive friction material characteristics using artificial neural networks-cold performance" in Wear, 261, no. 3-4 (2006):269-282, https://doi.org/10.1016/j.wear.2005.10.006 . .