船舶运动系统仿真与故障诊断  

Ship Motion System Simulation and Fault Diagnosis

作　　者：罗晴午 谢基榕[1] LUO Qingwu;XIE Jirong(China Ship Scientific Research Center,Wuxi 210482,Jiangsu,China)

机构地区：[1]中国船舶科学研究中心,江苏无锡214082

出　　处：《机电设备》2024年第5期92-98,共7页Mechanical and Electrical Equipment

摘　　要：为及时、准确地识别多舵多推进器的电力船舶运动系统所发生的故障,保障系统的正常运行,通过系统仿真获取数据集并以此进行船舶运动系统的故障诊断研究。首先,使用Modelica语言建立系统的仿真模型,分析运动系统常见机械故障,并仿真得到故障数据集,然后使用EfficientNet-b0-causal网络进行故障诊断,并与其他诊断模型进行对比。结果表明:所建诊断模型准确率达到98.08%,高于其他诊断模型的准确率;同时,其预测时间较短,具有较好的实时性。研究成果可为船舶运动系统的故障诊断提供一定参考。In order to timely and accurately identify faults in the electric ship motion system with multiple rudders and thrusters,and ensure the normal operation of the system.Datasets is obtained through system simulation to conduct fault diagnosis research on the ship motion system.First,Modelica language is used to establish a simulation model of the system,common mechanical faults in the motion system is analyzed,and simulate to obtain a fault dataset.Then,use EfficientNet-b0 causal network for fault diagnosis and compare it with other diagnostic models.The results show that the accuracy of the established diagnostic model reached 98.08%,which is higher than the accuracy of other diagnostic models.At the same time,its prediction time is short and it has good real-time performance.The research results can provide certain reference for the fault diagnosis of ship motion systems.

关 键 词：故障诊断 船舶运动系统 Modelica建模 EfficientNet-b0-causal 

分 类 号：U664[交通运输工程—船舶及航道工程]