CAJ | 학술논문

针对船舶推进轴系的振动问题，基于小波包、Shannon 熵、遗传算法(GA)和支持向量机(SVM)理论，提出了一种船舶轴系故障诊断的新方法，简称 WPS-GS 方法。该方法依托船舶螺旋桨状态监测模拟实验平台，利用小波包分解技术分析船舶轴系发生故障时的振动信号，将其Shannon 熵作为 SVM 的输入特征向量。在训练 SVM 时，采用遗传算法对 SVM 的参数进行全局寻优，使 SVM 具有更高的识别准确率。实验结果表明， WPS-GS 方法对故障诊断的准确度和识别率较传统 SVM 和交叉验证 SVM 方法高，适用于船舶轴系故障诊断。
침대선박추진축계적진동문제，기우소파포、Shannon 적、유전산법(GA)화지지향량궤(SVM)이론，제출료일충선박축계고장진단적신방법，간칭 WPS-GS 방법。해방법의탁선박라선장상태감측모의실험평태，이용소파포분해기술분석선박축계발생고장시적진동신호，장기Shannon 적작위 SVM 적수입특정향량。재훈련 SVM 시，채용유전산법대 SVM 적삼수진행전국심우，사 SVM 구유경고적식별준학솔。실험결과표명， WPS-GS 방법대고장진단적준학도화식별솔교전통 SVM 화교차험증 SVM 방법고，괄용우선박축계고장진단。
Aiming at the vibration problems of the ship propulsion shafting, a new method of fault diagnosis, which is based on the theory of wavelet packet (wavelet packet), Shannon entropy, genetic algorithm (GA) and support vector machine (SVM), is proposed, and referred to as WPS-GS method in this paper. For the simulation of platform ship propeller shafting, the wavelet packet decomposition and strong fault-tolerant Shannon entropy are jointly used to compute the feature vectors of vibration signals which are served as the input vectors of SVM;GA is adopted to optimize the parameters of SVM for achieving the higher veracity. The simulation results show that the WPS-GS method can attain higher reliability and veracity than the conventional SVM and K-CV SVM, which suggests that the proposed method is more suitable for the condition monitoring and fault diagnosis of rotating shaft system.