基于声发射技术的机械密封膜厚测量

机械密封主要通过动静端面之间的流体膜来实现润滑与密封，因此须对其膜厚进行监测。针对现有监测技术难以推广到工业现场的问题，提出机械密封液膜状态的声发射监测方法。以直接测量结果指导间接测量结果，建立适于声发射技术的机械密封液膜膜厚检定模型：对信号进行经验模态分解，并通过核主分量分析优化其特征；提出基于双重人工神经网络的联级决策模型。该模型能对密封膜厚程度进行估计，且较之单一的神经网络更为准确，具有良好的工业前景。

The Measurement of Film Thickness in Mechanical Seals based on AE Technology

Mechanical seals operated by a thin fluid film to separate the pair of seal faces for lubricating and sealing, so the film thickness needed to be measured. Because the current technique was not suit for industry, a method for measurement of film thickness of mechanical seals based on acoustic emission technique was presented. Through the direction of direct measurement, a detection model based on acoustic emission signal was built: first, the signal was processed by empirical mode decomposition, and kernel principal component analysis was used to optimize data features; then, a cascaded decision model based on artificial neural network was presented to estimate the film thickness. The model had better recognition rate than a single neural network, and had a wide industrial prospect.