Monitoring and Control Techniques in Metal Additive Manufacturing

Monitoring and Control Techniques in Metal Additive Manufacturing provides an overview of monitoring methods in metal additive manufacturing, demonstrating the use of manufacturing parameter control for quality improvement based on simulations and measurements. The implementation of structural health monitoring (SHM) methods to evaluate the quality of manufactured parts and detect defects is included. The book starts with chapters introducing metal additive manufacturing, discussing the benefits of integrating monitoring methods into the additive manufacturing process and the benefits of control mechanisms. The following chapter outlines various monitoring methods, including thermal sensors, vision sensors, non-destructive testing (including ultrasound, acoustic emission sensors, and radiography), and optical emission spectroscopy. From there, computational methods for the analysis of data and decision making are discussed, including statistical methods, machine learning techniques, and deep convolutional neural network approaches used for process visualization, analysis, and classification. Numerical methods used to estimate temperature, strain distribution, and cavity percentages are also covered, as are structural health monitoring methods. The book also features a chapter dedicated to real-world applications of these techniques, and concludes with a chapter evaluating the performance of the previously discussed methods as well as a look at future trends.