Fused deposition modeling (FDM) is one of the most popular additive manufacturing technologies for fabricating prototypes with complex geometry and different materials. However, current commercial FDM machines have the limitations in process reliability and product quality. In order to overcome these limitations and increase the levels of machine intelligence and automation, machine conditions need to be monitored more closely as in closedloop control systems. In this study, a new method for in situ monitoring of FDM machine conditions is proposed, where acoustic emission (AE) technique is applied. The proposed method allows for the identification of both normal and abnormal states of the machine conditions. The time-domain features of AE hits are used as the indicators. Support vector machines with the radial basis function kernel are applied for state identification. Experimental results show that this new method can potentially serve as a nonintrusive diagnostic and prognostic tool for FDM machine maintenance and process control.

No abstract

Grinding is usually done in the final finishing of a component. As a result, the surface quality of finished products, e.g., surface roughness, hardness and residual stress, are affected by the grinding procedure. However, the lack of methods for monitoring of grinding makes it difficult to control the quality of the process. This paper focuses on the monitoring approaches for the surface burn phenomenon in grinding. A non-destructive burn detection method based on acoustic emission (AE) and ensemble empirical mode decomposition (EEMD) was proposed for this purpose. To precisely extract the AE features caused by phase transformation during burn formation, artificial burn was produced to mimic grinding burn by means of laser irradiation, since laser-induced burn involves less mechanical and electrical noise. The burn formation process was monitored by an AE sensor. The frequency band ranging from 150 to 400 kHz was believed to be related to surface burn formation in the laser irradiation process. The burn-sensitive frequency band was further used to instruct feature extraction during the grinding process based on EEMD. Linear classification results evidenced a distinct margin between samples with and without surface burn. This work provides a practical means for grinding burn detection.

Despite its recent popularity, additive manufacturing (AM) still faces many technical challenges for the insufficiency of process reliability, controllability, and product quality. To enhance the process repeatability, effective in-situ monitoring methods for AM processes are needed. In this study, an online monitoring method for AM process failure detection is proposed, where acoustic emission (AE) is applied as the sensing technique. Its application to polymer material extrusion, also known as the technology of fused deposition modeling (FDM), is demonstrated. Experimental results show that the proposed monitoring method allows for the real time identification of major process failures. The occurring time of major failures and failure modes can be identified by analyzing the time- and frequency-domain features of AE hits respectively. A K-means clustering algorithm is applied to verify and demonstrate the classification procedure. The automated failure identification can reduce the waste of fabrication with enhanced machine intelligence.

No abstract