摘要
滚动轴承早期故障信号比较微弱,且受噪声与振动耦合影响,导致其故障判别失准。基于变分模态分解算法(VMD)与能量熵结合构建多模态特征矩阵,以灰狼算法(GWO)优化支持向量机(SVM)参数,提出VMD-Entropy-OSVM轴承智能故障诊断,采用轴承实验数据验证所提方法的有效性与优越性。实验结果表明:VMD-Entropy-OSVM不仅可识别轴承损伤末期的不同故障类型,且在识别损伤初期亦有较高准确度;在信噪比为8 dB下准确率高达99.8%,比现有方法提高3.3%~27.3%;当信噪比为0 dB下仍有73.5%的准确度,比现有方法提高11%~33%,该模型表现出良好的泛化性能;在相同计算资源下,所需运行时间更短,效率更高。
The early fault signals of rolling bearings are relatively weak,and are affected by the coupling of noise and vibration,which leads to inaccurate fault judgments.Based on variational mode decomposition(VMD)and energy entropy,multi-mode characteristic matrix is constructed.Grey wolf optimizer(GWO)is adopted to optimize the parameters of support vector machine(SVM).VMD-Entropy-OSVM bearing intelligent fault diagnosis is proposed,using bearing experimental data to verify the effectiveness and superiority of the proposed method.The experimental results show that VMD-Entropy-OSVM not only recognizes different fault types at the end of bearing damage,but also has high accuracy at the beginning of bearing damage.The accuracy of the proposed method is up to 99.8%at 8 dB,which is 3.3%~27.3%higher than the existing method.When the SNR is 0 dB,the accuracy is still 73.5%,which is 11%~33%higher than the existing method,the model shows good generalization performance.In addition,the running time is shorter and more efficient under the same computing resources.
作者
金江涛
许子非
李春
缪维跑
李根
JIN Jiang-tao;XU Zi-fei;LI Chun;MIAO Wei-pao;LI Gen(Energy and Power Engineering Institute,University of Shanghai for Science and Technology,Shanghai 200093,China;Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering,Shanghai 200093,China)
出处
《计量学报》
CSCD
北大核心
2021年第7期898-905,共8页
Acta Metrologica Sinica
基金
国家自然科学基金(51976131,51676131)
上海市“科技创新行动计划”地方院校能力建设项目(19060502200)。
关键词
计量学
智能故障诊断
滚动轴承
变分模态分解
能量熵
灰狼算法
支持向量机
优化
metrology
intelligent fault diagnosis
rolling bearing
variational mode decomposition
energy entropy
grey wolf optimizer
support vector machine
optimization
