粗糙集和最小二乘支持向量机的船舶汽轮工况分析

Rough set and least square support vector machine for marine steam turbine working condition analysis

汽轮是保证船舶正常航行的重要设备,对船舶汽轮工况进行分析具有重要意义,针对当前船舶汽轮工况分析方法误差大、效率低等不足,设计了基于粗糙集和最小二乘支持向量机的船舶汽轮工况分析方法。首先对当前船舶汽轮工况研究现状进行分析,找到船舶汽轮工况分析误差大、效率低的因素,然后从船舶汽轮工作状态信号中提取工况分析特征,通过粗糙集算法对工况分析原始特征进行约简处理,减少工况分析特征数量,提高船舶汽轮工况分析效率,最后约简处理后船舶汽轮工况分析特征作为最小二乘支持向量机的输入向量,船舶汽轮工况状态作为最小二乘支持向量机的输出向量,构建船舶汽轮工况分析模型,并进行船舶汽轮工况实例分析。本文方法得到令人满意的船舶汽轮工况分析结果,提高了船舶汽轮工况分析精度,船舶汽轮工况分析速度得到了大幅提升,比其他船舶汽轮工况分析模型具有更高的实际价值。

Steam turbine is an important equipment to ensure the normal navigation of ships.It is of great practical significance to analyze the working conditions of ship’s steam turbine.Aiming at the shortcomings of the current methods of analyzing the working conditions of ship’s steam turbine,such as large error and low efficiency,a method of analyzing the working conditions of ship’s steam turbine based on rough set and least squares support vector machine(LSSVM)is designed.Firstly,the analysis of the current ship steam turbine working condition is carried out on the spot,and the factors of large error and low efficiency are found.Then,the analysis characteristics of ship steam turbine working condition are extracted from the signal of ship steam turbine working condition.The original characteristics are reduced by rough set working condition analysis,so as to reduce the number of analysis features and improve the analysis efficiency of ship steam turbine working condition.Finally,the analysis efficiency of ship steam turbine working condition is improved after reduction.The characteristics of marine steam turbine condition analysis are used as input vectors of LS-SVM,and the state of marine steam turbine condition is used as output vectors of LS-SVM.The model of marine steam turbine condition analysis is constructed and an example of marine steam turbine condition is analyzed.Satisfactory results of ship steam turbine condition analysis are obtained by this method,which improves the accuracy of ship steam turbine condition analysis.The speed of ship steam turbine condition analysis has been greatly increased,and it has higher practical value than other ship steam turbine condition analysis models.