We present a method for deriving a strategy for stacking containers with uncertain weight information. Stacking the incoming containers according to our strategy, we can significantly reduce the number of container re-handlings at the time of loading. Since the rehandlings occur due to the error in estimated weight groups of containers, we devised a method which is sensitive to the probability distribution of true weight group given an estimated weight group. We implemented a simulated annealing algorithm which can find a good stacking strategy within a reasonable time. It was found that the number of re-handlings can be further reduced by improving the accuracy of weight grouping through the use of a learned classifier. The next step of our work would be to apply a cost sensitive learning for the weight classification because experimental results have shown that improvement of classification accuracy alone does not always lead to reduction of re-handling counts for some stacking strategies.
Deriving stacking strategies for export containers with uncertain weight information
Herleitung einer gewichtsabhängigen Stapelstrategie für Schiffscontainer
Journal of Intelligent Manufacturing ; 17 , 4 ; 399-410
2006
12 Seiten, 14 Bilder, 5 Tabellen, 20 Quellen
Aufsatz (Zeitschrift)
Englisch
Deriving Measurement Strategies from Science
British Library Conference Proceedings | 2005
|MOBILE HOUSING VEHICLE USING RECYCLED CONTAINERS FOR EXPORT
Europäisches Patentamt | 2022
|METHOD FOR STACKING CONTAINERS FOR TRANSPORTATION BY RAIL
Europäisches Patentamt | 2018
|