摘要
本文研究基于CBR的船舶故障诊断方法。用户通过应用接口在故障诊断窗口输入船舶故障征兆,推理机采用分级检索算法从案例库内搜索与所输入船舶故障征兆相近的案例。分级检索算法选取TOPSIS方法确定目标船舶故障案例所属类别,完成第一级检索;选取最近邻法和模板检索法结合,完成第二级检索方法。分级检索算法成功匹配船舶故障案例后,依据相似度阈值获取与该故障具有最高相似度的船舶故障指导案例,实现船舶故障诊断。实验结果表明,该方法可以有效诊断船舶空调系统、发动机等船舶不同部位故障,令船舶快速恢复正常运行状态。
A ship fault diagnosis method based on CBR is studied. The user inputs the ship’s fault symptoms in the fault diagnosis window through the application interface, and the inference engine uses a hierarchical retrieval algorithm to search the case database for cases similar to the input ship’s fault symptoms. The hierarchical retrieval algorithm selects the TOPSIS method to determine the category of the target ship failure case, and completes the first-level retrieval;selects the combination of the nearest neighbor method and the template retrieval method to complete the second-level retrieval method.After the hierarchical retrieval algorithm successfully matches the ship fault cases, it obtains the ship fault guidance cases with the highest similarity with the fault according to the similarity threshold, so as to realize the ship fault diagnosis. The experimental results show that the method can effectively diagnose the faults of different parts of the ship such as the ship’s airconditioning system and the engine, so that the ship can quickly return to normal operation.
作者
王涛
WANG Tao(Academic Affaires Office,Jiangsu Maritime Institute,Nanjing 211170,China)
出处
《舰船科学技术》
北大核心
2022年第9期166-169,共4页
Ship Science and Technology
基金
江苏省教育改革项目(2017JSJG315)。
关键词
CBR
船舶
故障诊断
推理机
案例库
相似度
CBR
ship
fault diagnosis
inference engine
case library
similarity
