Fused Filament Fabrication (FFF) is one of the most popular additive manufacturing technologies for manufacturing prototypes with various complex geometries. However, current commercial FFF machines have limitations in terms of process reliability and product quality. In order to overcome these limitations and improve the accuracy and reliability of these machines, a real-time monitoring system is needed to make sure that any part defects can be detected during the printing process and printing parameters can be identified that can be modified to resolve the printing anomalies resulting in minimization of waste and improvement of efficiency. In this study, a method for in-situ monitoring of FFF machine conditions is proposed utilizing an acoustic emission (AE) technology. The AE sensor is used to monitor the vibration signals generated during the whole printing process in real-time. The AE signal is then analyzed and processed, and categorized according to the selected objective characteristics. The proposed method can be utilized to identify the abnormal states of machine conditions. The time-domain features of AE hits after post-processing are used as key indicators. Experimental results show that this method has the potential to be used as a non-invasive diagnostic and prognostic tool for FFF machine maintenance and process control.