Diamond-Coated Mechanical Seal Remaining Useful Life Prediction Based on Convolution Neural Network

Abstract

Reliable remaining useful life (RUL) prediction of industrial equipment key components is of considerable importance in condition-based maintenance to avoid catastrophic failure, promote reliability and reduce cost during the production. Diamond-coated mechanical seal is one of the most critical wearing components in petroleum chemical, nuclear power and other process industries. Estimating the RUL is of critical importance. We consider the data-driven approaches for diamond-coated mechanical seal RUL estimation based on AE sensor data, since it is difficult to construct an explicit mathematical degradation model of seal. The challenges of this work are dealing with the noisy AE sensor data and modeling the degradation process with fluctuation. Faced with these challenges, we propose a pipeline method CDF-CNN to estimate the RUL for mechanical seal: WPD-KLD to raise the signal-to-noise ratio, novel CDF-based statistics to represent seal degradation process and CNN structure to estimate RUL. To acquire AE sensor data, several diamond-coated seals are tested from new to failure in three working conditions. Experimental results demonstrate that the proposed method can accurately predict the RUL of diamond-coated mechanical seal based on AE signals. The proposed prediction method can be generalized to other various mechanical assets.

Friction and Wear Characteristics of Cr-CNTs Composite Coating End Faces of High-Temperature Mechanical Seals

“…With the increasing demand for improved contact mechanical seal end face performance, mechanical seal end face surface modification technology has been widely used, and composite coatings in high-parameter condition mechanical seals have made significant progress in research [1][2][3][4]. The composite coating is essential to improve the seal end face's stability and wear resistance and to extend the mechanical seal's life [5][6][7][8].…”

A Double-Channel Hybrid Deep Neural Network Based on CNN and BiLSTM for Remaining Useful Life Prediction

“…The nonparametric statistical process is used to update the prediction. In addition to the above neural network prediction models, models based on self-organizing mapping (SOM) and the backpropagation (BP) neural network model [ 24 ], support vector machine (SVM) model [ 25 , 26 ], convolutional neural network (CNN) [ 27 ], recurrent neural network (RNN) [ 28 , 29 ], and other models are also applied to RUL prediction. At present, most models cannot fully extract the features of each dimension with multidimensional big data samples.…”