عنوان المقالة:Studying the Condition Based Maintenance Dataset of Naval Propulsion Plants Using Regression ANN Studying the Condition Based Maintenance Dataset of Naval Propulsion Plants Using Regression ANN
Mohamad Mehyo; Hakan Özcan; Ahmed Hassan Ahmed Hassan
English Authors
Mohamad Mehyo; Hakan Özcan; Ahmed Hassan Ahmed Hassan
Abstract
In this work, applying and experimenting various options effects of a feed-foreword artificial neural network (ANN) which used to obtain regression model that predicts GT Compressor decay state coefficient and GT Turbine decay state coefficient of naval propulsion plants. Based on 16 inputs. Dataset is obtained from an open online source, consists of huge amount of data point, 11935 data points have been carried out by means of a numerical simulator of a naval vessel (Frigate) characterized by a Gas Turbine (GT) propulsion plant. The different blocks forming the complete simulator (Propeller, Hull, GT, Gear Box, and Controller) have been developed and fine-tuned over the year on several similar real propulsion plants. In view of these observations, the available data are in agreement with a possible real vessel. Many neural networks are created and trained with various settings and sub-datasets and then compared to observe the effect of each variation. After the factors which affect the learning operation was studied. It is taken some of the data in order to test the best ANN that had been learned by taking 20 random values from all data and compare their results with the actual outputs.
Abstract
In this work, applying and experimenting various options effects of a feed-foreword artificial neural network (ANN) which used to obtain regression model that predicts GT Compressor decay state coefficient and GT Turbine decay state coefficient of naval propulsion plants. Based on 16 inputs. Dataset is obtained from an open online source, consists of huge amount of data point, 11935 data points have been carried out by means of a numerical simulator of a naval vessel (Frigate) characterized by a Gas Turbine (GT) propulsion plant. The different blocks forming the complete simulator (Propeller, Hull, GT, Gear Box, and Controller) have been developed and fine-tuned over the year on several similar real propulsion plants. In view of these observations, the available data are in agreement with a possible real vessel. Many neural networks are created and trained with various settings and sub-datasets and then compared to observe the effect of each variation. After the factors which affect the learning operation was studied. It is taken some of the data in order to test the best ANN that had been learned by taking 20 random values from all data and compare their results with the actual outputs.
Publication Date
5/3/2019
Publisher
3nd International Students Science Congress 3-4 May 2019, Izmir - Turkey
احمد حسن احمد حسن | Ahmed Hassan Ahmed Hassan | 4895