No abstract

No abstract

Data-driven prognostic approaches like Gaussian Process combined with Unscented Kalman Filter (GPUKF) are promising methods for predicting the Remaining Useful Lifetime (RUL) of a degrading component. Whereas the Gaussian Process (GP) is appropriate to derive a suitable degradation model by means of a set of training data, the Unscented Kalman Filter (UKF) employs this model to determine the prediction and its uncertainty.Since a degradation process is highly stochastic, it is assumed that by applying more sets of training data the accuracy and precision of the GPUKF is increased. In order to examine the performance enhancement two different approaches are investigated in this paper: First, a single GP is trained with all available data sets. The second approach combines several GPs (each created with a data set of one degradation process) by extending the GPUKF with a Multiple Model Method. The development of a third prognostic approach aims at the investigation of the UKF as a suitable tool for the prognostic algorithm. Therefore, a third method applies a Particle Filter in combination with the GP. For the evaluation of the aforementioned prognosis algorithms according to their precision and accuracy a set of prevalent performance metrics like the Prognostic Horizon and the Mean Average Percentage Error of a prediction is analyzed.The validity of the determined results is increased by considering the variance of certain metrics over several units under test. Moreover, particular focus is set on the examination of the performance change caused by the use of more training data sets. In order to quantify this process known metrics are extended. The evaluation is based on simulated data sets, which are generated by an exponential degradation model. The analysis of the implemented algorithms indicates that the applied metrics are in a comparable range. However, the three approaches reveal a different behaviour concerning the convergenceof the performance values according to the number of training data. In particular cases there is even a decline in accuracy and precision attend by a rising number of training data.

No abstract

The data acquisition of run to failure data by means of de- grading components is one of the most delicate tasks in evaluating new diagnostic and prognostic approaches, since it is cost-intensive and time-consuming. Therefore, a test rig for a cost-efficient generation of artificial bearing damages is described below. The test rig is thereby based on an ordinary asynchronous motor. This paper mainly concentrates on the description of the test rig’s setup and first diagnostic findings. One aim of the experiments is the investigation of several variations of the applied loads for the artificially accelerated bearing aging. Thus, radial force and fluting are examined. The latter causes a damage triggered by a current flow through the test bearing. Both load types reduce the overall lifespan of bearings to about few weeks. The generated faults are a broken cage and chattermarks due to a radial force higher than the design point. The bearings are diagnosed by means of frequency analysis of the phase current signal, which is produced in the stator of the motor. Beside the current signal, also temperature, vibration and revolution of the shaft are measured, whereas the vibration signal is used only for the comparison to the current signal. The comprehensive measurement concept allows a performance evaluation of diagnostic and prognostic algorithms based on different physical indicators. It can be shown that especially the current frequency spectrum of a faulty bearing differs significantly from a healthy one. In order to face the high amount of measurement data, the Principal Component Analysis is used for data reduction to generate features for the diagnosis and prognosis. Thus, a classification of different fault modes and loading conditions is possible.