The detection and identification of faults in rotary machines are of great significance to the mechanical equipment reliability especially the gearbox. Traditional machine learning algorithms suffer from low diagnosis accuracy of faults that have multiple types and exist concurrently. A novel machine learning method called hierarchical machine learning (HML) was proposed in this study to improve the faults diagnosis accuracy. The proposed algorithm consists of two layers. The first layer comprises a traditional machine learning model to identify the faults with distinguishable features and filter out these faults with indistinguishable features. The second layer model recognizes the faults filtered out by the first layer. In order to verify the effectiveness of the proposed method, the gearbox simulation experiment is carried out in the study. The simulation results validate that the proposed method outperforms other algorithms under an identical measure.

旋转机械故障的检测和识别对机械设备尤其是齿轮箱的可靠性具有重要意义。传统的机器学习算法对多类型并发存在的故障诊断准确率不高。本研究提出了一种称为分层机器学习（HML）的新型机器学习方法，以提高故障诊断的准确性。所提出的算法由两层组成。第一层包括传统的机器学习模型，用于识别具有可区分特征的故障并过滤掉具有不可区分特征的故障。第二层模型识别第一层过滤掉的故障。为了验证所提方法的有效性，在研究中进行了齿轮箱仿真实验。