摘要
空压机作为船舶航行过程中的关键设备,其运行状态的精准识别对船舶安全性能具有重要影响。鉴于空压机在工作过程中振动信息呈现出非平稳和非线性的特点,提出利用监督核熵成分分析对其特征数据选择,旨在通过数据降维保留关键特征信息,将处理后的特征信息输入到经过贝叶斯优化方法优化超参数的支持向量机模型中,以评估其在空压机状态识别方面的性能。经实验验证可知,该方法能够有效提升支持向量机模型的识别准确率,准确率可达98.47%。
As a key equipment in the process of ship navigation,the accurate identification of the operation status of the air compressor has an important impact on the safety performance of the ship.In view of the non-stationary and nonlinear characteristics of the vibration information of the air compressor during the working process,the supervised nuclear entropy component analysis was proposed to select the characteristic data.Aiming to retain the key feature information through data dimensionality reduction,the processed feature information was input into the support vector machine model optimized by Bayesian optimization method to optimize the hyperparameters,so as to evaluate its performance in the state recognition of the air compressor.Experimental results showed that the proposed method can effectively improve the recognition accuracy of the support vector machine model,with an accuracy rate of 98.47%.
作者
赵凯
王永坚
蔡杭溪
李劼
ZHAO Kai;WANG Yong-jian;CAI Hang-xi;LI Jie(School of Marine Engineering,Jimei University,Xiamen Fujian 361021,China)
出处
《船海工程》
北大核心
2025年第1期13-19,共7页
Ship & Ocean Engineering
基金
福建省自然科学基金(2020J01687)。
关键词
船用空压机
阀片故障诊断
监督核熵成分分析
贝叶斯优化
支持向量机
marine air compressors
valve plate fault diagnosis
supervised kernel entropy component analysis
Bayesian optimization
support vector machine
