In-situ porosity recognition for laser additive manufacturing of 7075-Al alloy using plasma emission spectroscopy

Abstract

Poor quality and low repeatability of additively manufactured parts are key technological obstacles for the widespread adoption of additive manufacturing (AM). In-situ monitoring and control of the AM process is vital to overcome this problem. This paper describes the combined artificial intelligence and plasma emission spectroscopy to identify the porosity of AM parts during the process. The time- and position-synchronized spectra were collected during the directed energy deposition (DED) manufacturing process of a 7075-Al alloy part. Eighteen features extracted from spectra were coupled with the deposition qualities which were characterized by the 3D X-ray Computed Tomography (CT) scan and used to train a Random Forest (RF) classifier. The well-trained RF classifier achieved up to 83% precision for the porosity recognition of depositions. The feature importance recorded by the RF classifier indicates that the intensities of spectra at the wavelength of 414.234 (Fe I) nm and 396.054 (Al I) nm, and the kurtosis of spectra at wavelength ranges of 484–490 nm and 508–518 nm, are the most effective features for porosity recognition. The physical correlations between spectra, porosity formation, and thermal accumulation during the AM process were analyzed. This study demonstrates the great potentials, as well as challenges of plasma emission spectroscopy for in-situ quality monitoring of laser AM which allows the enhancement of AM technique.

Application of nonlinear ultrasonic analysis for in situ monitoring of metal additive manufacturing

“…21 Recently, several methods have been designed for real-time porosity inspection during AM by online monitoring of melt-pool features (e.g., temperature, geometry, and radiation intensity). 22–26 Although these methods can examine porosity with a high accuracy, a large amount of iterative testing is required to establish a new relationship between the melt pool features and porosity once the target AM process or material is changed. In addition, the authors proposed a femtosecond laser-based transient thermoreflectance (TTR) measurement system for in situ porosity inspection.…”

Selection of effective manufacturing conditions for directed energy deposition process using machine learning methods

“…Metal additive manufacturing (AM) technology has emerged in the aircraft, automobile, and shipbuilding industries, and can realize designs that are not possible using conventional manufacturing methods 1 . Metal AM technologies can be classified into powder bed fusion (PBF) and direct energy deposition (DED) processes.…”

DLAM: Deep Learning Based Real-Time Porosity Prediction for Additive Manufacturing Using Thermal Images of the Melt Pool

“…In addition, researchers were able to proscribe laser control techniques to mitigate keyhole formations [27] and a method to predict keyhole sizes based on laser intensity [26]. However, access to X-Ray imaging technology is still cost prohibitive for widespread commercial use and other research has focused around utilizing infrared, near infrared, photo diodes and optical cameras to analyze thermal information from the melt pool [33]- [47]. Researchers have shown that melt pool widths and lengths can be estimated [43]- [45] and abnormalities detected [37] directly by extracting and analyzing simple metrics and statistical measures.…”

“…Another research group was able to show that graph Fourier transform coefficients could be derived from two different photo diode sensors, and when these coefficients were used as input features for machine learning models, each model showed an improved accuracy in predicting porosity volume by layer compared to conventional metrics and statistical features [38]. Others have analyzed the aggregate thermal data of melt pools within a given layer and used Isolated Decision Trees [36] and Random Forest (RF) [47] models to detect anomalous melt pools and therefore predict porosities within that layer. Finally, a research group was able to utilize a pre-trained Convolutional Neural Networks (CNN) to predict whether a porosity existed at a location and its cross-sectional volume for a single-layer, single-track part, when optical images of the melt pool were input into the model in a frame-by-frame manner [40].…”

“…While the layer-wise methods proposed in previous research can be used to detect porosity during the AM process, catching an error in frame-by-frame would allow for a higher quality feedback loop [34], [36], [38], [42], [46], [47]. Others have relied upon simple metrics to detect melt pool anomalies in real-time, but these methods may not reliably scale due to their over-simplification of complex phenomena occurring during the AM process [37], [39], [43]- [45].…”