基于PSO-ELM算法实现船舶发电机组故障识别  

Fault Identification of Marine Generator Set Based on PSO-ELM Algorithm

作　　者：尚前明[1] 姜苗 陈辉[1] 路鹏 SHANG Qianming;JIANG Miao;CHEN Hui;LU Peng(School of Energy and Power Engineering,Wuhan University oflechnologj^Wuhan 430063,China)

机构地区：[1]武汉理工大学能源与动力工程学院,武汉430063

出　　处：《船舶工程》2021年第1期87-94,共8页Ship Engineering

基　　金：中电科(宁波)海洋电子研究院有限公司项目(20183h0513);国家自然科学基金浙江两化融合联合基金重点项目(U1709215)。

摘　　要：针对船舶发电机组的不同故障类型,通过传感器采集不同故障下柴油机缸盖处的振动信号,构成大量数据集,选取部分数据集作为样本数据。通过EEMD算法对样本数据进行分解降噪,把一维数据分解成能反映柴油机工况信息的多维数据,对分解形成的多维数据使用KICA算法进行特征提取,并对提取后的数据进行训练集、验证集分组。使用PSO-ELM算法搭建故障识别模型,并使用训练集训练模型,使用验证集验证模型,根据验证结果评价模型是否满足故障识别的精确度。Vibration signals at the cylinder head of diesel engine under different faults are collected by sensors for different fault types of marine generator sets, forming a large number of data sets. Some data sets are selected as sample data. EEMD algorithm is used to decompose the sample data to reduce noise, and the one-dimensional data is decomposed into multidimensional data that can reflect the working condition information of the diesel engine. KICA algorithm is used to extract the features of the decomposed multidimensional data, and the extracted data are grouped into training sets and verification sets. The PSO-ELM algorithm is used to build the fault recognition model, the training set is used to train the model, and the verification set is used to verify the model. According to the verification results, whether the model meets the fault identification accuracy is evaluated.

关 键 词：船舶发电机组 故障识别 POS ELM EEMD算法 KICA算法 

分 类 号：U665.1[交通运输工程—船舶及航道工程]