基于ISSA-ELM的船舶压载水系统故障诊断研究  

Fault diagnosis of ship ballast water system based on ISSA-ELM

作　　者：王曼绮 曹辉[1,2] 张琦 张宝中 WANG Manqi;CAO Hui;ZHANG Qi;ZHANG Baozhong(Marine Engineer College,Dalian Maritime University,Dalian 116026,China;Dalian Maritime University Smart Ship Limited Company,Dalian 116026,China;Marine Design and Research Institute of China,Shanghai 200001,China)

机构地区：[1]大连海事大学轮机工程学院,辽宁大连116026 [2]大连海大智船科技有限责任公司,辽宁大连116026 [3]中国船舶及海洋工程设计研究院,上海200001

出　　处：《舰船科学技术》2024年第19期36-41,共6页Ship Science and Technology

基　　金：辽宁省自然资源厅项目(1638882993269);辽宁省科技厅项目(2022JH1/10800097)。

摘　　要：为了从船舶压载水系统中有效挖掘数据信息,降低极限学习机(ELM)初始参数随机性对故障诊断精度的影响,提出基于改进麻雀搜索算法(ISSA)优化ELM的船舶压载水系统故障诊断模型。首先,使用自适应加权策略和Levy飞行策略改进发现者位置公式,获得ISSA并验证其性能;而后利用改进后的麻雀搜索算法对ELM的初始输入权重和阈值进行优化,建立基于ISSA-ELM的故障诊断模型。结果表明,ISSA-ELM模型的故障诊断精度为96.6%,比SSAELM、PSO-ELM、GWO-ELM模型高出1.8%、3.5%和2.6%,比ELM和SVM模型高出4.5%和7.1%。In order to effectively mine data information from ship ballast water systems and reduce the impact of initial parameter randomness of Extreme Learning Machine(ELM)on fault diagnosis accuracy,a ship ballast water system fault diagnosis model based on improved Sparrow Search Algorithm(ISSA)optimized ELM is proposed.Firstly,using adaptive weighting strategy and Levy flight strategy to improve the discoverer position formula,obtaining ISSA and verifying its per-formance;Then,the improved sparrow search algorithm is used to optimize the initial input weights and thresholds of ELM,and a fault diagnosis model based on ISSA-ELM is established.The experimental results show that the fault diagnosis accur-acy of ISSA-ELM model is 96.6%,which is 1.8%,3.5%,and 2.6%higher than SSA-ELM,PSO-ELM,and GWO-ELM models,and 4.5%and 7.1%higher than ELM and SVM models.

关 键 词：船舶压载水系统 故障诊断 极限学习机(ELM) 改进麻雀搜索算法(ISSA) 

分 类 号：U664.83[交通运输工程—船舶及航道工程]