Vibration-Based Fault Diagnosis of Broken Impeller and Mechanical Seal Failure in Industrial Mono-Block Centrifugal Pumps Using Deep Convolutional Neural Network

被引:28
作者
Manikandan, S. [1 ]
Duraivelu, K. [1 ]
机构
[1] SRM Inst Sci & Technol, Kattankulathur Campus, Chennai, Tamil Nadu, India
关键词
Vibration signals; Fault diagnosis; Broken impeller; Seal failure; Deep convolution neural network; EMPIRICAL MODE DECOMPOSITION; FEATURE-EXTRACTION; ALGORITHM;
D O I
10.1007/s42417-022-00566-0
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Purpose Hydraulic pump failure results in a high rate of energy loss, performance degradation, high vibration levels, and continuous noise emission. An unexpected pump failure might result in a sudden collapse of the hydraulics, resulting in significant financial losses and the shutdown of the whole factory. Fault diagnosis plays a critical function in diagnosing flaws before they occur. Early detection is crucial for identifying problems and may save money, time, and potentially dangerous circumstances. Methods In recent years, many studies in intelligent fault diagnosis utilizing various machine learning approaches have been conducted. A vibration-based fault diagnosis in industrial mono-block centrifugal pumps is presented in this study. An experimental configuration for structuring databases, required for developing algorithms for running machine learning programs, is designed. Standard condition vibration signals are collected from the setup when the pump is healthy and free of defects. This study considers the two major defective conditions of broken impeller (B.I.) and seal failure (S.F.). The faults are introduced in the pump one after the other, and the vibration signals are obtained. The image processing approach converts these analog signals to 2D images. Results Later, the images are trained and tested using a deep convolution neural network (DCNN) classifier, and the fault accuracy is verified. The results show an accuracy of 99.07% after training and testing the image dataset. Conclusion The suggested DCNN architecture exhibits high and accurate fault diagnosis accuracy for the industrial mono-block centrifugal pump.
引用
收藏
页码:141 / 152
页数:12
相关论文
共 43 条
[41]   Fault Diagnosis for a Wind Turbine Generator Bearing via Sparse Representation and Shift-Invariant K-SVD [J].
Yang, Boyuan ;
Liu, Ruonan ;
Chen, Xuefeng .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2017, 13 (03) :1321-1331
[42]  
Ye Tian, 2015, Applied Mechanics and Materials, V764-765, P191, DOI [10.4028/www.scientific.net/amm.764-765.191, 10.4028/www.scientific.net/AMM.764-765.191]
[43]   A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox [J].
Zhang, Kai ;
Tang, Baoping ;
Deng, Lei ;
Liu, Xiaoli .
MEASUREMENT, 2021, 179