Joint probability distributions of correlation coefficients in the diagnostics of mobile work machines

In this paper, we address the problem of diagnostics of mobile hydraulic work machines. A diagnostics method based on the comparison of measurement data of a HIL-simulator and a real mobile work machine using a real time simulation model of an articulated-frame-steered wheel loader is presented. The proposed method includes two phases: training and testing. We use similar set of drive sequences in both phases. In the training phase, the behaviour of an undamaged machine is modelled by probability density functions, which are then used to detect anomalies in the testing phase. In both phases, first, the time series data of multiple variables are segmented into segments of the same length. Correlation coefficients are then calculated for each segment and the distributions of the correlation coefficients are estimated by computing probability density functions using histograms. Finally, the joint probabilities that the correlations in the data segments of the time series data are observed are calculated using the already computed histograms. In faulty systems, occurrence of correlation coefficients changes, which can be used to detect anomalies by comparing the training and testing joint probabilities. The diagnostics is finally based on the combination of static threshold and threshold based on mean value of joint probabilities. This enables the detection of both the single segments with low joint probability value, which indicates high probability of an anomaly, and also the changing trends in the joint probabilities. Simulated faults in the main hydraulic components of the hydrostatic transmission and the working hydraulics of mobile work machine were used as anomalies to study the changes in the joint probability values and to verify the diagnostics method. Finally, the efficacy and the sensitivity of the proposed diagnostics method is presented with promising results regarding detection of faults situations of mobile work machine.