Early damage detection and classification by condition monitoring systems is crucial to enable predictive maintenance of manufacturing systems and industrial facilities. Data analysis can be improved by applying machine learning algorithms and fusion of data from heterogenous sensors. This paper presents an approach for a step-wise integration of classifications gained from vibration and acoustic emission sensors in order to combine the information from signals acquired in the low and high frequency ranges. A test rig comprising a drive train and bearings with small artificial damages is used for acquisition of experimental data. The results indicate that an improvement of damage classification can be obtained using the proposed algorithm of combining classifiers for vibrations and acoustic emissions.
Using additive manufacturing to generate a polymer–metal structure offers the potential to achieve a complex customized polymer structure joined to a metal base of high stiffness and strength. A tool to evaluate the generated interface during the process is of fundamental interest, as the sequential deposition of the polymer as well as temperature gradients within the substrate lead to local variations in adhesion depending on the local processing conditions. On preheated aluminum substrates, 0.3 and 0.6 mm high traces of polylactic acid (PLA) were deposited. Based on differential scanning calorimetry (DSC) and rheometry measurements, the substrate temperature was varied in between 150 and 200 °C to identify an optimized manufacturing process. Decreasing the layer height and increasing the substrate temperature promoted wetting and improved the adhesion interface performance as measured in a single lap shear test (up to 7 MPa). Thermographic monitoring was conducted at an angle of 25° with respect to the substrate surface and allowed a thermal evaluation of the process at any position on the substrate. Based on the thermographic information acquired during the first second after extrusion and the preset shape of the polymer trace, the resulting wetting and shear strength were estimated.
1 October 2025 in e-Journal of Nondestructive Testing
Permanently installed sensor systems are becoming increasingly important for monitoring critical infrastructure. The research institutes Fraunhofer IZFP and BAM, together with industrial partners and users, are developing a concept for an electronic system consisting of an Edge-Gateway as a central high-performance node and a variable number of Sensor-Edge units that establish the connection between the sensors of the permanent monitoring system and the gateway, which also provides connection to a cloud. A software tool allows identification and localization of sensors and visualization of sensor data. The principle of the system is demonstrated using sensors installed in the road surface to monitor traffic loads as an example. Two test structures, a full-scale laboratory at Fraunhofer IZFP, Saarbrücken, and the “BLEIB” reference structure at BAM, test site technical safety (TTS) Horstwalde, were used to demonstrate the principle and the functioning of the electronic system.