Detecting faults in hydraulic valves are of great significance to improve the reliability and security of the whole hydraulic system. However, it is difficult to detect multiple faults in hydraulic valves using existing approaches due to closed structural components and complex hydraulic system itself. Therefore, an intelligent fault diagnosis approach based on Dempster-Shafer (DS) theory is proposed specifically for detecting several faults occurred in hydraulic valves. Actually, it is classified in the ensemble learning in terms of the information fusion theory. In this approach, signal segments containing fault information are selected to structure sample sets firstly. Then sample sets are simultaneously fed into the single classifier including long short-term memory networks (LSTM), convolutional neural network (CNN) and random forests (RF). Through learning spontaneously in these intelligent classification approaches, fault features are concluded and the probability of each type fault is respectively revealed. All probabilities are constructed as basic probability assignment (BPA) functions, which are further calculated in the information fusion process in terms of DS theory. Finally, the fault types are identified by the final fusion results. Experimental investigations are performed to validate performance of the present approach (taken a solenoid controlled pilot operated directional valve as an example). It is shown that the average accuracy ratio of proposed intelligent fault diagnosis approach is 98.5% for six fault types detection. The study does provide an effective access to detect faults in hydraulic valves.

检测液压阀故障对提高整个液压系统的可靠性和安全性具有重要意义。然而，由于封闭的结构部件和复杂的液压系统本身，使用现有方法难以检测液压阀中的多个故障。因此，提出了一种基于DS理论的智能故障诊断方法，专门用于检测液压阀中发生的几种故障。实际上，它是在集成学习中根据信息融合理论进行分类的。在这种方法中，首先选择包含故障信息的信号段来构造样本集。然后将样本集同时输入到单个分类器中，该分类器包括长短期记忆网络（LSTM），卷积神经网络（CNN）和随机森林（RF）。通过自发地学习这些智能分类方法，可以得出故障特征并分别揭示每种类型故障的概率。所有概率均构造为基本概率分配（BPA）函数，并在信息融合过程中根据DS理论对其进行进一步计算。最后，通过最终融合结果确定故障类型。进行实验研究以验证本方法的性能（以电磁阀控制的先导式换向阀为例）。结果表明，提出的智能故障诊断方法在六种故障类型检测中的平均准确率为98.5％。该研究确实为检测液压阀故障提供了有效途径。