Loading management is one of the most important technologies for ship power system. Reasonable distribution of electric energy to the loading can achieve the goal of optimal energy schedule and its primary issue is to make a reasonable loading priority evaluation. This paper analyzed the shortcomings of the loading priority evaluation using the AHP and proposed a kind of algorithm of property weight evaluation based on PRISM classification, effectively combing expertise and characteristics of the objective data itself together. The results show that: the loading priority of ship power system is mainly affected by two properties of demand urgency and vulnerability. The results of various algorithms are basically consistent with the above conclusion, which proved the correctness of the algorithm. Comparison among various evaluation results tables shows that for the same weight measurement standard using different classification algorithm or property reduction algorithms, the results of its loading priority evaluation slightly differ.
[1]
Chester R. Petry,et al.
ZONAL ELECTRICAL DISTRIBUTION SYSTEMS: AN AFFORDABLE ARCHITECTURE FOR THE FUTURE
,
1993
.
[2]
Ian H. Witten,et al.
Data mining: practical machine learning tools and techniques, 3rd Edition
,
1999
.
[3]
Robert C. Baker,et al.
TWENTY STEPS TO A BETTER FLEET: INSURV REVIEW OF SURFACE SHIP DESIGN ENGINEERING
,
1985
.
[4]
Ian H. Witten,et al.
Chapter 15 – Embedded Machine Learning
,
2011
.
[5]
Vergil B. Smith.
AIRCRAFT CARRIER ELECTRICAL POWER SYSTEM DESIGN PRACTICES
,
1977
.
[6]
Jadzia Cendrowska,et al.
PRISM: An Algorithm for Inducing Modular Rules
,
1987,
Int. J. Man Mach. Stud..
[7]
John Cerminara,et al.
Ship service electrical systems: designing for survivability
,
1990
.