Generalised statistical process control (GSPC) in condition monitoring
Abstract
The early detection of fluctuations in operating conditions and fault detection can be done with similar methods. Advanced statistical analysis provides tools for the feature extraction based on generalised norms and moments. Intelligent stress indices are calculated from these features by the nonlinear scaling, which also uses the norms and moments, improves sensitivity to small fluctuations. In condition monitoring cases, the indices are consistent with the vibration severity criteria. The parameters of the scaling functions define suitable control limits for the features and indices. Harmfully high levels of stress are efficiently detected with control limits adjusted to the process requirements. The solution can be extended to the analysis of fluctuations, recursive tuning and linked with fatigue risk estimation. Intelligent trend indices, episodes and deviation indices can be analysed in the same way. The limits can be explained by fuzzy set systems and categorical information is included through knowledge-based analysis. The generalised statistical process control (GSPC) extends SPC to nonlinear and non-Gaussian data: the new approach is suitable for a large set of statistical distributions. It operates without interruptions in short run cases and adapts to the changing process requirements. Control charts based on scaled values and indices are combined by artificial and computational intelligence.
