Additive manufacturing (AM) is an important production trend. Meanwhile, the lack of an online defect detection technology is a key problem that limits the further development of AM. To realize effective online monitoring of defects, an online melt pool defect detection method and system for the laser engineered net shaping (LENS) printing process is proposed in this study. The online temperature measurement system of the melt pool with a single camera was integrated into the LENS printing equipment. Synchronous monitoring of the printing process was realized, and images of the temperature distribution and evolution of the melt pool with high resolution were obtained online. A defect detection method, called temperature distribution similarity detection (TDSD) method, is proposed. The TDSD method is mainly based on the similarity of the global distribution or the front heating region of the temperature field in the melt pool. According to the abnormal characteristics caused by surface defects in the temperature field in the melt pool, defects can be detected efficiently online. "External boundary alignment, internal correlation detection" strategy is proposed for similarity detection, and the printing quality database, including temporal and spatial characteristics of all points in the melt pool under the influence of artificial defects can be established. By optimizing the detection coverage, the sensitivity of defect identification can be significantly improved, and abnormal characteristics, such as substrate defects and spatter can be identified more accurately. The experimental results indicated that surface pore defects with a diameter of over 25 µm could be detected, the defect detection accuracies exceeded 90%, and the relative location error was approximately 6.4% in the case of a horizontal substrate. The developed method has practical application prospects for online surface defects detection and is of significance to the abnormal feedback and quality control in the AM process. 

Online defect detection method and system based on similarity of the temperature field in the melt pool

Industry 4.0 represents a significant change in manufacturing with the inclusion of such technologies as additive manufacturing and data analytics. In support of these changes, infrared thermal imaging (IR) and very-near infrared (VNIR) have proven invaluable in numerous applications related to additive manufacturing. In this review, these applications will be presented as they relate to polymer and metal-based additive manufacturing processes. Applications including in-situ characterization, post-build analysis, experimental setups, modeling, and machine learning will be covered. With a general overview complete, the review will conclude with a discussion of challenges identified throughout the literature and thoughts on future trends.

A survey of thermal sensing application in additive manufacturing

Online in-situ monitoring of melt pool characteristic based on a single high-speed camera in laser powder bed fusion process

Research on synchronous measurement technique of temperature and deformation fields using multispectral camera with bilateral telecentric lens

Stability of molten pool temperature directly affects the dimensional accuracy, metallurgical defects, solidification microstructure and mechanical properties of formed parts manufactured by laser metal deposition technology. Therefore, the optimization of the macroscopic morphology and microstructure of the formed parts through the stable control of the molten pool temperature has been intensively studied. In this study, three models, based on the back propagation neural network (BPNN), random forest (RF) algorithms and response surface methodology (RSM) approach, respectively, were used to establish prediction relationships between the deposition input parameters and processing status parameters, geometric morphology and mechanical property parameters. Then, the processing temperature and molten pool characteristics of thirty groups of 316L stainless steel single-track cladding layers were analyzed. The prediction results show that the average prediction error (APE) of the prediction of molten pool temperature, track width, track height and micro-hardness of the deposited layer based on BPNN model are 0.5%, 1.3%, 2.9% and 0.1%, respectively, which are better than the prediction results of RF and RSM models. Then, BPNN model was further used to predict the molten pool temperature and processing quality of the deposited layer under the combination of five new process parameters groups. Objective of this study was to lay the foundation for the subsequent design of the molten pool temperature control system to improve the morphology accuracy and mechanical properties of formed parts. 

Kai Zhao

Papers

Real-time measurement method of melt pool temperature in the directed energy deposition process