Extraction Methods of Multi - Fault Information in Machine Condition Monitoring

Abstract

An outline of the multi-fault diagnostic observation concept is presented in the paper. Starting from the commonly used Singular Value Decomposition (SVD) it is shown, that it is equivalent to the modern version of Principal Component Analysis (PCA). During the development of the concept of multi-fault observation several indices and measures obtained from SVD were tried, and some seem to bring the success. This problem is also addressed in the paper and illustrated by real examples taken from railroad Diesel engine condition monitoring.

State of mechanical condition applied to industrial machines based on SVD method

“…The dataset have been analyzed with an algorithm called Computer System of Identification Investigations (SIBI). SIBI algorithm was used to validate the research results [2,16] also, these measures have a high sensitivity to the mechanical variation, which allows the identification of the mechanical condition.…”

“…SD i is a sensible symptom of a specific failure and therefore, each SD i is used to identify a failure between different symptoms that evolve in the system. SD i contains independent information about the failure mode and also on the intensity of this failure [2,12].…”

“…Polish Standard -PN-) or international standards (e.g. ISO) [2]. But, to determine the mechanical condition of a machine, the natural vibration process during the lifetime can be used as source of information [3].…”

Estimation of combustion engine technical state by multidimensional analysis using SVD method

“…An advance of the failure F i (θ k ) in the operation time θ k can be described through the SD i (θ k ) discriminant. Therefore, it is possible to affirm that (Cempel et al, 2003) ( ) ( )…”

“…Source: Żółtowski and Cempel (2004), Cempel (2005b) and Żółtowski et al (2008) The main diagonal of the matrix Σ pr , becomes the eigenvalues Λ, it has a physical interpretation, Λ = [μ 1 ,…,μ i ,…,μ k ] represents the fraction of damage (contribution of fault) in the engineering systems, the set of μ i has a limited value attached λ lim , and it represents failure of the first failure status μ 1 . By using the SVD method it is possible to determine SD i the index, which is defined as the discriminant of the failure i th (Cempel et al, 2003). SD i is a sensible symptom to a specific failure and therefore each SD i is used for distinguishing between various failures that evolve in the system.…”