Acoustic Emission is the process of continuous monitoring of the mechanical vibrations (i.e. sound) in a structure. The vibrations are sensed by the Acoustic Emission transducers and subsequently recorded in a data acquisition device and computer. Acoustic Emission has traditionally been used in applications such as monitoring of large structures (e.g. bridges) and machinery (e.g. power generators). The usage has then typically been focused on the evaluation of the level of vibration. Transient vibrations with high amplitude, so-called acoustic events, or the general noise level are examples of features in the recorded signals that have been used to detect cracking phenomena or break down of machinery. In more recent years, along with the increase of computing power, the evaluation and analysis of Acoustic Emission data has developed. This in turn has broadened the scope and applications that are relevant for Acoustic Emission monitoring. Furthermore, with improved availability of machine learning algorithms this has become even more evident. In our research at Högskolan Väst we use Acoustic Emission for monitoring and evaluation of Additive Manufacturing (AM) processes. For this project we study two AM processes: Powder Bed Fusion Laser (PBF-Laser) and Direct Energy Deposition Laser (DED-Laser). In both processes metallic materials such as Titanium and Nickel-based super alloys are used. In a layer-by-layer fashion, the metallic material (powder or wire) is melted by the laser to form the final component. The processes can be interpreted as a form of metallic 3D printing. However, the processes are associated with several challenges. For instance, the issue of temperature is a topic of particular interest since it is related to the build-up of residual stress in the component. This can ultimately lead to crack formations or other defects. In addition to temperature, several other process parameters and strategies for manufacturing are of key importance. Research shows that Acoustic Emission is successfully used in monitoring of metal-based Additive Manufacturing (AM). The basic principle is that a known acoustic signature (e.g. “fingerprint”) is established for the process and the machine state. Deviations from this known signature (“fingerprint”) are then used as indicators of an unstable process condition. This implies that potential formation of anomalies and defects can be predicted already at the manufacturing stage as well as cracking due to residual stress. In our project we aim to further investigate, explore and develop the use of Acoustic Emission in metal-based Additive Manufacturing (AM). In addition to evaluation of the Acoustic Emission data on its own we also aim to extend the evaluation to potentially include other sensor data such as pyrometer data (temperature), i.e. so-called sensor-fusion approaches.