Wyniki wyszukiwania - BazTech

1

Effect of ship neural domain shape on safe and optimal trajectory

Lisowski J.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2023

|

Vol. 17 No. 1

185--191

EN

This article presents the task of safely guiding a ship, taking into account the movement of many other marine units. An optimally neural modified algorithm for determining a safe trajectory is presented. The possible shapes of the domains assigned to other ships as traffic restrictions for the particular ship were subjected to a detailed analysis. The codes for the computer program Neuro-Constraints for generating these domains are presented. The results of the simulation tests of the algorithm for a navigational situation are presented. The safe trajectories of the ship were compared at different distances, changing the sailing conditions and ship sizes.

2

Modeling of supercritical boiler by neural network

Lichota Janusz

Rynek Energii

|

2023

|

Nr 4

64--69

EN

This article presents an artificial neural network (ANN)-based modeling approach for predicting the performance and emissions of a supercritical coal-fired boiler. The NN model was developed using a large dataset of historical boiler operation data, which include inputs like fuel flow rate, air flow rate, and steam pressure, as well as outputs such as boiler efficiency and emissions of pollutants such as NOx. The results indicate that the NN model is able to accurately predict the performance and emissions of the supercritical boiler, with a high coefficient of determination for the training, validation, and test sets. The results of this study demonstrate the potential of NN-based modeling for improving the efficiency and emissions of supercritical boilers and for providing valuable insights into the complex relationships between the inputs and outputs of these systems. The model presented in the article can be used to answer a question whether it is possible to obtain the same generated power at a higher efficiency or lower emissions using different control signals.

PL

W artykule przedstawiono podejście do modelowania oparte na sztucznej sieci neuronowej (ANN) służące do przewidywania wydajności i emisji kotła opalanego węglem na parametry nadkrytyczne. Model NN opracowano przy użyciu dużego zbioru danych historycznych dotyczących działania kotła, który obejmuje dane wejściowe, takie jak natężenie przepływu paliwa, natężenie przepływu powietrza i ciśnienie pary, a także dane wyjściowe, takie jak wydajność kotła i emisja substancji zanieczyszczających, takich jak NOx. Wyniki wskazują, że model NN jest w stanie dokładnie przewidzieć wydajność i emisję kotła na parametry nadkrytyczne, przy wysokim współczynniku determinacji dla zestawów szkoleniowych, walidacyjnych i testowych. Wyniki tego badania pokazują potencjał modelowania opartego na NN w zakresie poprawy wydajności i emisji kotłów na parametry nadkrytyczne oraz dostarczenia cennych informacji na temat złożonych relacji między wejściami i wyjściami tych systemów. Zaprezentowany w artykule model może posłużyć do odpowiedzi na pytanie, czy przy zastosowaniu różnych sygnałów sterujących możliwe jest uzyskanie tej samej generowanej mocy przy wyższej sprawności lub mniejszej emisji.

3

A small wind turbine output model for spatially constrained remote island miicro-grids

Žigman D., Meštrović K., Tomiša T.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2022

|

Vol. 16 No. 1

143--146

EN

Modelling operation of the power supply system for remote island communities is essential for its operation, as well as a survival of a modern society settled in challenging conditions. Micro-grid emerges as a proper solution for a sustainable development of a spatially constrained remote island community, while at the same time reflecting the power requirements of similar maritime subjects, such as large vessels and fleets. Here we present research results in predictive modelling the output of a small wind turbine, as a component of a remote island micro-grid. Based on a month-long experimental data and the machine learning-based predictive model development approach, three candidate models of a small wind turbine output were developed, and assessed on their performance based on an independent set of experimental data. The Random Forest Model out performed competitors (Decision Tree Model and Artificial Neural Network Model), emerging as a candidate methodology for the all-year predictive model development, as a later component of the over-all remote island micro-grid model.