摘要
针对电机转子故障信号非平稳、敏感的故障特征不能有效提取,传统分类器参数智能优化算法存在优化速度慢、调整参数多、易陷入局部最优等问题提出基于ICEEMDAN-MSE-KPCA与NGO-HKELM优化的转子故障诊断方法。首先,采用改进的自适应噪声完全集合经验模态分解(improved complete empirical mode decomposition with adaptive noise,ICEEMDAN)方法对转子振动信号进行分解和重构;计算重构信号的多尺度样本熵(multiscale sample entropy,MSE),形成特征向量,通过核主成分分析(kernel principal component analysis,KPCA)方法对高维的特征向量进行降维;最后,将降维后的特征向量输入北方苍鹰算法(northern goshawk optimization,NGO)优化的混合核极限学习机(hybrid extreme learning machine,HKELM)进行转子故障分类。研究结果表明,基于ICEEMDAN-MSE-KPCA与NGO-HKELM优化的转子故障诊断模型,平均识别准确率可达97.7273%,平均寻优时间为1.0681 s,收敛速度快、准确率高以及分类效果好。
In view of the non-stationary and sensitive fault features of motor rotor fault signals,the traditional classifier parameter intelligent optimization algorithm has some problems,such as slow optimization speed,too many adjustment parameters,and easy to fall into local optimum.A rotor fault diagnosis method based on ICEEMDAN-MSE-KPCA and NGO-HKELM optimization is proposed.Firstly,the improved complete empirical mode decomposition with adaptive noise(ICEEMDAN)method is used to decompose and reconstruct the rotor vibration signals;Multiscale sample entropy(MSE)of reconstructed signals was calculated to form feature vectors.Kernel principal component analysis(KPCA)was used to reduce the dimensionality of high-dimensional feature vectors;Finally,the dimensionally reduced feature vector was input into the hybrid extreme learning machine(HKELM)optimized by the northern goshawk optimization(NGO)algorithm for rotor fault classification.The results show that the rotor fault diagnosis model optimized by ICEEMDAN-MSE-KPCA and NGO-HKELM has an average recognition accuracy of 97.7273%and an average search time of 1.0681 s,with fast convergence,high accuracy and good classification effect.
作者
陆水
李振鹏
李军
颜东梅
黄福川
LU Shui;LI Zhenpeng;LI Jun;YAN Dongmei;HUANG Fuchuan(College of Mechanical Engineering,Guangxi University,Nanning 530105,China;Guangxi Key Laboratory of Petrochemical Resources Processing and Process Strengthening Technology,Guangxi University,Nanning 530105,China;Intelligent Agriculture Research Institute,Guangxi Institute of Industry and Research,Guangxi University,Nanning 530105,China)
出处
《组合机床与自动化加工技术》
北大核心
2024年第4期175-180,共6页
Modular Machine Tool & Automatic Manufacturing Technique
