Variable Selection Methods in Dredger Production Model
The production of earthwork is an important index to evaluate the performance of dredgers. Because the parameters affecting production are numerous and not independent of each other, it is easy to overfit the production model and have low accuracy. In view of this problem, based on the measured data of a Trailing Suction Hopper Dredger (TSHD), three variable selection methods are applied to select the parameters that can affect the yield most and the inputs of the final production model are determined. The results show that the deleted and retained parameters conform to the actual working conditions. Finally, the advantages and disadvantages of these three methods and their applicability under different working conditions of dredgers are analyzed.
KeywordsHopper dredging Yield model Variable selection
This work was financially supported by the Science and Technology Commission of Shanghai Municipality of China under Grant (No. 17511107002).
- 1.Increased accuracy in data for Dutch dredging operations. World Pumps, 2017(26), 28–29 (2017)Google Scholar
- 2.Braaksma, J., Babuska, R., Klaassens, J.B., et al.: Model predictive control for optimization the overall dredging performance of a trailing suction hopper dredger. In: Proceedings of the 18th World Dredging Congress (2007)Google Scholar
- 8.Moradi, M.H., Abedini, M.: A combination of genetic algorithm and particle swarm optimization for optimal DG location and sizing in distribution systems. Int. J. Electr. Power Energy Syst. 1, 66–74 (2011)Google Scholar
- 9.Zhang, Z.: An estimation of coal density distributions by weight based on image analysis and MIV-SVM. In: 2015 IEEE Advanced Information Technology Electronic and Automation Control Conference (2015)Google Scholar