| 1. |
- Hjorth Simonsen, Martin, 1988, et al.
(författare)
-
State-of-the-art within ship weather routing
- 2015
-
Ingår i: Proceedings of The ASME 2015 34th International Conference on Ocean, Offshore and Arctic Engineering (OMAE 2015). - 9780791856499 ; , s. 1-11
-
Konferensbidrag (refereegranskat)abstract
- Increased fuel prices and public awareness of environment impacts from shipping have attracted large efforts in maritime sector to increase its energy efficiency as a factor of competitiveness. Weather routing has become a recognized measure, which can partly help to achieve the targets as well as enhancing safety. A routing system requires a reliable optimization algorithm to consider a ship’s operational costs, expected time of arrival, and cargo safety etc. simultaneously. Hence, the service provided by a weather routing system is highly dependent on a properly selected optimization algorithm and associated input parameters. In this paper the concept of weather routing is broken down into many elements for further analysis. Focus is given to algorithms, constraints and weather forecasts used in the optimized routing plan. Two different aspects of state-of-the-art have been considered. The first is a study of software already in use and the second is a study of methods investigated in the research community. Furthermore, this paper also provides examples of development trends, for example the fatigue based routing, and the risk based routing, as well as its integration with onboard monitoring systems for more reliable weather and ship specific response information.
|
|
| 2. |
- Larsson, Erik, 1988, et al.
(författare)
-
DIRECT Optimization Algorithm for Ship Routing Plan
- 2015
-
Ingår i: Proceedings of the International Offshore and Polar Engineering Conference. 25th International Offshore and Polar Engineering Conference, ISOPE-2015, Hawaii, 21-26 June 2015.. - 1098-6189.
-
Konferensbidrag (refereegranskat)abstract
- Weather routing represents one increasingly recognized method for reducing fuel consumption, hereby lowering emissions and costs. This paper provides a short outline of the general concept of weather routing of ships, while focus is on the implementation of the DIRECT (DIviding RECTangles) algorithm in the construction of a novel weather routing tool made in cooperation with Maersk Maritime Technology. The developed routing tool is demonstrated on several conceptual cases to determine capabilities of route profiles avoiding obstacles such as land, avoiding adverse storms by varying voyage speed and utilizing weather to schedule a route with minimized fuel consumption. Strengths and weaknesses of the utilization of the DIRECT algorithm are discussed.
|
|
| 3. |
- Larsson, Erik, 1988, et al.
(författare)
-
DIRECT optimization algorithm in weather routing of ships
- 2015
-
Ingår i: Proceedings of the International Offshore and Polar Engineering Conference. - 1098-6189 .- 1555-1792. - 9781880653890 ; 2015-January, s. 1207-
-
Konferensbidrag (refereegranskat)abstract
- Weather routing represents one increasingly recognized method for reducing fuel consumption, hereby lowering emissions and costs. This paper provides a short outline of weather routing of ships, while focus is on the implementation of the DIRECT (Dividing RECTangles) algorithm in the construction of a novel weather routing tool made under supervision from Maersk Maritime Technology. It is evaluated on several conceptual cases to determine capabilities of route profiles avoiding obstacles such as adverse storms by varying voyage speed and utilizing weather to schedule a route with rmnimized fuel consumption. This paper discusses the application of the developed routing tool for shortest route, land avoidance, storm avoidance and combinations. Strengths and weaknesses of the utilization of the DIRECT algorithm are discussed.
|
|
| 4. |
|
|
| 5. |
- Stepien, Hubert, et al.
(författare)
-
A novel method for detecting uavs using parallelneural networks with re-inference
- 2022
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we present a novel method for detecting UAVs using diverse parallel neural networks with re-inference. The parallel networks are of type Convolutional Neural Networks (CNNs). We first set up a lowthreshold (2 respectively 20%) for each of the individual networks to detect a flying object. If all networks detecta flying object in the same area of a video frame with some overlap, we zoom into that area and redo the objectdetection and classification (re-inference step). To ensure correctness and reliability of the results from severalparallel CNNs, we introduce total confidence Tc as a measurement. We also introduce the intersection overunion for multiple parallel networks, IoUAll , and use that as threshold for calculating a reliable Tc . The resultsshow great improvements regarding accurate detection of flying drones, reduced mispredictions of otherobjects as drones, and fast response time when drones disappear from the scene.
|
|
