基于SSA-SVM算法的船舶LFCS故障诊断
Fault Diagnosis of Ship Low Freshwater Cooling System LFCS Based on SSA-SVM Algorithm
尹衍楚 1邹永久 1杜太利 1张跃文1
作者信息
- 1. 大连海事大学轮机工程学院,辽宁 大连 116026
- 折叠
摘要
船舶低温淡水系统作为保障船舶动力装置安全运行的动力系统,一旦发生故障仅依靠轮机员很难及时排除故障.针对支持向量机(support vector machine,SVM)在模式识别方面受自身参数选择影响较大的问题,提出了基于麻雀搜索算法(sparrow search algorithm,SSA)优化支持向量机的故障诊断方法.利用麻雀搜索算法(SSA)优化了支持向量机的惩罚参数和核参数,建立了基于SSA-SVM的船舶低温淡水系统故障诊断模型.结果表明,SSA-SVM诊断模型比传统的支持向量机(SVM)和粒子群算法(particle swarm optimization,PSO)优化的支持向量机诊断模型的准确率分别高 28%和5%,且收敛速度更快.SSA-SVM算法对船舶低温淡水系统的常见故障进行有效地诊断,能为轮机设备的健康管理及轮机员的诊断决策提供一定的指导.
Abstract
As a power system to ensure the safe operation of the ship's power plant,the ship's fresh water cooling-system is difficult to troubleshoot in time only by the engineer crew once a failure occurs.Aiming at the problem that the support vector machine(SVM)is greatly affected by its own parameter selection in pattern recognition,a fault di-agnosis method based on sparrow search algorithm(SSA)optimized support vector machine was proposed.The SSA was used to optimize the penalty parameters and kernel parameters of support vector machine,and the fault diagnosis model of ship lowfresh water coolingsystem based on SSA-SVM was established.The results show that the accuracy of SSA-SVM model is 28%and 5%higher than that of traditional SVM and particle swarm optimization(PSO),respec-tively,and the convergence rate is faster.The SSA-SVM algorithm can effectively diagnose the common faults of the ship's fresh water cooling system,and can provide certain guidance for the health management of marine equipment and the diagnostic decision of the engineer.
关键词
支持向量机/麻雀搜索算法/故障诊断/算法优化Key words
Support vector machine/Sparrow search algorithm/Fault diagnosis/Algorithm to optimize引用本文复制引用
基金项目
国家自然科学基金(52101400)
国家自然科学基金(52101345)
出版年
2024
NETL
NSTL
维普
万方数据