Abstract
Check valve is one of the most important components and most easily damaged parts in high pressure diaphragm pump, which is a typical representative of reciprocating machinery. In order to ensure the normal operation of the pump, it is necessary to monitor its running state and diagnose fault. However, in the fault diagnosis of check valve, the classification models with single kernel function can not fully interpret the classification decision function, and meanwhile unreasonable assumption of diagnostic cost equalization has a significant impact on classification results. Therefore, the multikernel function and cost-sensitive mechanism are introduced to construct the fault diagnosis model of check valve based on the multikernel cost-sensitive extreme learning machine (MKL-CS-ELM) in this paper. The comparative test results of check valve for high pressure diaphragm pump show that MKL-CS-ELM can obtain fairly or slightly better performance than ELM, CS-ELM, MKL-ELM, and multikernel cost-sensitive support vector learning machine (MKL-CS-SVM). At the same time, the presented method can obtain very high accuracy under imbalance datasets condition and effectively overcome the weakness of diagnostic cost equalization and improve the interpretability and reliability of the decision function of classification model. It, therefore, is more suitable for the practical application.
Highlights
High pressure diaphragm pump is the most important equipment for high concentration slurry pipeline transportation
In the binary classification experiments, the datasets of Normal condition (NC) and NK are selected as the test data
(5) From the experimental results, we can see that the multikernel learning mechanism is helpful to further improve the diagnostic performance of the classification models
Summary
High pressure diaphragm pump is the most important equipment for high concentration slurry pipeline transportation. The research of condition monitoring and fault diagnosis of the high pressure diaphragm pump has important practical significance in promoting development of slurry pipeline transportation field. In order to complete the condition monitoring and fault diagnosis of reciprocating machineries effectively, both domestic and foreign scholars have introduced the fault diagnosis methods of rotating machinery into the fault diagnosis of reciprocating machinery and made many valuable research results [3,4,5]. The research results have provided effective theoretical support for accident prevention and pipeline maintenance and greatly reduced maintenance costs. Compared with the fault diagnosis of rotating machinery, there are still many research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
