Weber, Wolfgang

Autoencoders are widely used in many scientific disciplines for their good performance as so-called building blocks of deep learning. Furthermore, they have a pronounced capability for dimensionality reduction. In this paper it is shown that autoencoders can additionally be used not only to detect but to qualify dependencies among the parameters of input data sets. For doing so, a two-step approach is proposed. Herein, the identical mapping of the input data to the output layer is done with a stacked autoencoder. Evaluating respective sensitivity measures yields the sought interrelations between the input parameters, if there are any. To verify the new approach, numerical experiments are conducted with synthesized data where linear or nonlinear dependencies between the input parameters are known a priori. It is shown that the two-step approach automatically detects these dependencies for all investigated cases.

One possibility to extend the service life of engi-neering structures is to provide adequate maintenance based on Structural Health Monitoring (SHM). Typically, SHM involves a sensor network which is spatially distributed at the surface or within the structure to be monitored. Each sensor measures at least one physical quantity, the data of all sensors then have to be properly evaluated to derive the health state and to predict the remaining service life. Health issues may be detected by machine learning methods by looking for anomalous behaviour in sensor data. Hereby the problem is that malfunctions differ excessively in the representation of the data collected by sensors such that specialisation of methods on anomaly types is required. The current contribution suggests the simulation of sensor malfunction based on established criteria by creating different types of artificial anomalous data indicating different types of issues. Several proposed autoencoder approaches are verified for different anomaly representations, which are artificially introduced in a set of data. The final solutions are different autoencoder specialized on different types of simulated anomaly data, making the conclusions drawn from the measured data more reliable. As a case study, data of a numerical experiment of fibre pull-out are considered.

© 2021, The Author(s). Up to now, the role of particle sizes on the impact behavior of ceramic particles in aerosol deposition not yet fully understood. Hence, with the aim to supply a more general understanding, modeling series of low strain rate compression and high-speed impact were performed by molecular dynamics on single-crystalline particles in sizes of 10-300 nm that are tuned to match mechanical properties of TiO2-anatase. The modeling results reveal that particles with original diameter of 25-75 nm exhibit three different impact behaviors that could be distinguished as (i) rebounding, (ii) bonding and (iii) fragmentation, depending on their initial impact velocity. In contrast, particles larger than 75 nm do not exhibit the bonding behavior. Detailed stress and strain field distributions reveal that combination of “localized inelastic deformation” along the slip systems and “shear localization” cause bonding of the small and large particles to the substrate. The analyses of associated temperature rise by the inelastic deformation revealed that heat diffusion at these small scales depend on size. Whereas small particles could reach a rather homogeneous temperature distribution, the evolved heat in the larger ones keeps rather localized to areas of highest deformation and may support deformation and the formation of dense layers in aerosol deposition.