One of the major challenges of implementing additive manufacturing (AM) processes for the purpose of production is the lack of understanding of its underlying process-structure-property relationship. Parts manufactured using AM technologies may be too inconsistent and unreliable to meet the stringent requirements for many industrial applications. The first objective of the present research is to characterize the underlying thermo-physical dynamics of AM process, captured by melt pool signals, and predict porosity during the build. Herein, we propose a novel porosity prediction method based on the temperature distribution of the top surface of the melt pool as the AM part is being built. Advance data analytic and machine learning methods are then used to further analyze the 2D melt pool image streams to identify the patterns of melt pool images and its relationship to porosity. Furthermore, the lack of geometric accuracy of AM parts is a major barrier preventing its use in mission-critical applications. Hence, the second objective of this work is to quantify the geometric deviations of additively manufactured parts from a large data set of laser-scanned coordinates using an unsupervised machine learning approach. The outcomes of this research are: 1) quantifying the link between process conditions and geometric accuracy; and 2) significantly reducing the amount of point cloud data required for characterizing of geometric accuracy.

Hydrodynamic plain bearings are important machine elements. They are used in many areas of mechanical engineering, such as turbomachines, crankshaft bearings and gears. The geometry of the lubrication gap elemen-tarily influences the function as shown in several examples of abrupt failures in turbochargers. Due to toleranc-ing, the manufacturing requirements are very high. However, the question remains how large these deviations can be. ISO 12129-2 gives recommendations on form deviations depending on the minimum of plain bear-ing clearance (hmin). Nevertheless, there is no direct reference on the size or the strain on bearing. In DIN 31652-3, the tolerance of the bearing clearance is divided into -1/3 and +2/3 of itself. However, this tolerance merely has an indirect correlation with the size of the bearing and strain on the bearing. If these tolerance recommenda-tions are applied, the function of the plain bearing will not be completely fulfilled. Nonetheless, tolerances pro-vided by standards are used in geometric specifications. If these tolerances are used for in-company manufacturing, this is unproblematic in most cases. But if technical drawings are sent to an external manufacturer, toler-ance limits may be exhausted and the function cannot be ensured. Within the framework of the research project presented here, a tolerance evaluation matrix has been developed. For this, the existing standards were analyzed. In this case, the ignorance of size (diameter and width) and signif-icant operating properties (speed, load, temperature, etc.) are insufficient. The project examined and simulated various possible deviations. Selected form deviations were manufactured. The validation of the simulation results were carried out on 30mm.