Liu Jie, Hu Youmin, Wu Bo, Wang Yan, Xie Fengyun
School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China.
Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA.
Sensors (Basel). 2017 May 18;17(5):1143. doi: 10.3390/s17051143.
The operating condition of rolling bearings affects productivity and quality in the rotating machine process. Developing an effective rolling bearing condition monitoring approach is critical to accurately identify the operating condition. In this paper, a hybrid generalized hidden Markov model-based condition monitoring approach for rolling bearings is proposed, where interval valued features are used to efficiently recognize and classify machine states in the machine process. In the proposed method, vibration signals are decomposed into multiple modes with variational mode decomposition (VMD). Parameters of the VMD, in the form of generalized intervals, provide a concise representation for aleatory and epistemic uncertainty and improve the robustness of identification. The multi-scale permutation entropy method is applied to extract state features from the decomposed signals in different operating conditions. Traditional principal component analysis is adopted to reduce feature size and computational cost. With the extracted features' information, the generalized hidden Markov model, based on generalized interval probability, is used to recognize and classify the fault types and fault severity levels. Finally, the experiment results show that the proposed method is effective at recognizing and classifying the fault types and fault severity levels of rolling bearings. This monitoring method is also efficient enough to quantify the two uncertainty components.
滚动轴承的运行状况会影响旋转机械加工过程中的生产率和质量。开发一种有效的滚动轴承状态监测方法对于准确识别运行状况至关重要。本文提出了一种基于混合广义隐马尔可夫模型的滚动轴承状态监测方法，该方法使用区间值特征来有效地识别和分类机械加工过程中的机器状态。在所提出的方法中，利用变分模态分解（VMD）将振动信号分解为多个模态。VMD的参数以广义区间的形式提供了对偶然不确定性和认知不确定性的简洁表示，并提高了识别的鲁棒性。采用多尺度排列熵方法从不同运行条件下分解后的信号中提取状态特征。采用传统主成分分析来减小特征规模和计算成本。利用提取的特征信息，基于广义区间概率的广义隐马尔可夫模型用于识别和分类故障类型及故障严重程度等级。最后，实验结果表明所提出的方法在识别和分类滚动轴承的故障类型及故障严重程度等级方面是有效的。这种监测方法在量化两个不确定性分量方面也足够高效。
