Fault Detection of Reciprocating Compressors using a Model from Principles Component Analysis of Vibrations

Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals originating from the many different impact sources and wide ranges of practical operating conditions. In this paper Principal Component Analysis (PCA) is used for selecting vibration feature and detecting different faults in a reciprocating compressor. Vibration datasets were collected from the compressor under baseline condition and five common faults: valve leakage, inter-cooler leakage, suction valve leakage, loose drive belt combined with intercooler leakage and belt loose drive belt combined with suction valve leakage. A model using five PCs has been developed using the baseline data sets and the presence of faults can be detected by comparing the T2 and Q values from the features of fault vibration signals with corresponding thresholds developed from baseline data. However, the Q -statistic procedure produces a better detection as it can separate the five faults completely.

[1]  Ratko Grbic,et al.  Fault tolerant system in a process measurement system based on the PCA method , 2011, 2011 Proceedings of the 34th International Convention MIPRO.

[2]  Chenn-Jung Huang,et al.  A comparative study of feature selection methods for probabilistic neural networks in cancer classification , 2003, Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence.

[3]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[4]  Wenxian Yang,et al.  Establishment of the mathematical model for diagnosing the engine valve faults by genetic programming , 2006 .

[5]  Teresa Orlowska-Kowalska,et al.  Neural networks application for induction motor faults diagnosis , 2003, Math. Comput. Simul..

[6]  Theodora Kourti,et al.  Statistical Process Control of Multivariate Processes , 1994 .

[7]  Fengshou Gu,et al.  Use of the Smoothed Pseudo-Wigner-Ville Distribution , 1995 .

[8]  Bo-Suk Yang,et al.  Condition classification of small reciprocating compressor for refrigeration using artificial neural networks and support vector machines , 2005 .

[9]  Barry M. Wise,et al.  The process chemometrics approach to process monitoring and fault detection , 1995 .

[10]  Desire L. Massart,et al.  Projection methods in chemistry , 2003 .

[11]  J. Piper,et al.  On fully automatic feature measurement for banded chromosome classification. , 1989, Cytometry.

[12]  Thomas E. Marlin,et al.  Multivariate statistical monitoring of process operating performance , 1991 .

[13]  John F. MacGregor.  STATISTICAL PROCESS CONTROL OF MULTIVARIATE PROCESSES , 1994 .

[14]  Ashraf Saad,et al.  Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems , 2007, Appl. Soft Comput..

[15]  Fengshou Gu,et al.  Feature Selection and Fault Classification of Reciprocating Compressors using a Genetic Algorithm and a Probabilistic Neural Network , 2011 .

[16]  A. J. Morris,et al.  Application of exponentially weighted principal component analysis for the monitoring of a polymer film manufacturing process , 2003 .

[17]  S. Joe Qin,et al.  Multivariate process monitoring and fault diagnosis by multi-scale PCA , 2002 .

[18]  Biswanath Samanta,et al.  Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm , 2004, EURASIP J. Adv. Signal Process..

[19]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .