Automatic fault detection with condition and stress indices enables reliable condition monitoring to be combined with process control. Useful information on different faults can be obtained by selecting suitable features. Generalised norms can be defined by the order of derivation, the order of the moment and sample time. These norms have the same dimensions as the corresponding signals. The nonlinear scaling used in the linguistic equation approach extends the idea of dimensionless indices to nonlinear systems. The Wöhler curve is represented by a linguistic equation (LE) model. The contribution of the stress is calculated in each sample time, which is taken as a fraction of the cycle time. The cumulative sum of the contributions indicates the degrading of condition and the simulated sums can be used to predict failure time. To avoid high stress situations, the statistical process control (SPC) is extended to nonlinear and non-Gaussian data: the new generalised SPC is suitable for a large set of statistical distributions. It operates without interruptions in short run cases and adapts to the changing process requirements. The scaling functions are updated recursively, which is triggered by a fast increase of the deviation indices. The higher levels, which are rough estimates in the beginning, are gradually refined.