Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing

Gaikwad, Aniruddha; Williams, R. J. P.; Winton, Harry de; Bevans, Benjamin; Smoqi, Ziyad; Rao, Prahalada; Hooper, Paul A.

doi:10.1016/j.matdes.2022.110919

Cited by 34 publications

(10 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The etched micrograph of C2, the highest density specimen, shows melt pool penetration (Figure 13) without severe keyhole formation and a melt pool depth of approximately 90 µm. The depth of the best-performing specimen C2 was deeper than the optimum penetration (~55 µm) suggested in the analysis of Gaikwad [38]. The melt pool width, mostly defined by the laser spot diameter, was measured to be 90 µm.…”

Section: Optical Tomography Values and Process Windowmentioning

confidence: 82%

Metal Laser-Based Powder Bed Fusion Process Development Using Optical Tomography

Björkstrand,

Akmal,

Salmi

2024

Materials

View full text Add to dashboard Cite

In this study, a set of 316 L stainless steel test specimens was additively manufactured by laser-based Powder Bed Fusion. The process parameters were varied for each specimen in terms of laser scan speed and laser power. The objective was to use a narrow band of parameters well inside the process window, demonstrating detailed parameter engineering for specialized additive manufacturing cases. The process variation was monitored using Optical Tomography to capture light emissions from the layer surfaces. Process emission values were stored in a statistical form. Micrographs were prepared and analyzed for defects using optical microscopy and image manipulation. The results of two data sources were compared to find correlations between lack of fusion, porosity, and layer-based energy emissions. A data comparison of Optical Tomography data and micrograph analyses shows that Optical Tomography can partially be used independently to develop new process parameters. The data show that the number of critical defects increases when the average Optical Tomography grey value passes a certain threshold. This finding can contribute to accelerating manufacturing parameter development and help meet the industrial need for agile component-specific parameter development.

show abstract

Section: Optical Tomography Values and Process Windowmentioning

confidence: 82%

Metal Laser-Based Powder Bed Fusion Process Development Using Optical Tomography

Björkstrand,

Akmal,

Salmi

2024

Materials

View full text Add to dashboard Cite

show abstract

“…High-speed imaging by a laser at a fine spatiotemporal scale has been used to monitor molten pools. Although this monitoring technique has been used in previous work, adopting it for in situ process mapping is limited due to the poorly observable features 14 , low algorithmic accuracy 15 , and the need to use a complex setup and installation to obtain temperature field measurements 16 , 17 , which may require imaging alignment, calibration, and a special setup that needs to be integrated with the scanning head of the 3D printing machine.…”

Section: Introductionmentioning

confidence: 99%

Accelerating process development for 3D printing of new metal alloys

Guirguis,

Tucker,

Beuth

2024

Nat Commun

View full text Add to dashboard Cite

Addressing the uncertainty and variability in the quality of 3D printed metals can further the wide spread use of this technology. Process mapping for new alloys is crucial for determining optimal process parameters that consistently produce acceptable printing quality. Process mapping is typically performed by conventional methods and is used for the design of experiments and ex situ characterization of printed parts. On the other hand, in situ approaches are limited because their observable features are limited and they require complex high-cost setups to obtain temperature measurements to boost accuracy. Our method relaxes these limitations by incorporating the temporal features of molten metal dynamics during laser-metal interactions using video vision transformers and high-speed imaging. Our approach can be used in existing commercial machines and can provide in situ process maps for efficient defect and variability quantification. The generalizability of the approach is demonstrated by performing cross-dataset evaluations on alloys with different compositions and intrinsic thermofluid properties.

show abstract

“…42,43 In some cases, sensor fusion techniques were implemented using comprehensive NNs that consider multiple types of in situ detection. 44 Lee et al 45 employed a NN model on melt pool images to determine powder flow anomalies in a directed energy deposit AM system. The NN was trained on four specific fault cases in addition to the healthy case.…”

Section: Introductionmentioning

confidence: 99%

“…34 Additionally, these models use labeled datasets, which often require human input to determine if certain process phenomena is significant enough to constitute a fault. 44 Many faults need to be classified individually to train a NN for detection, lengthening the data collection process. For many systems, classifying and labeling these individual faults is not feasible.…”

Section: Introductionmentioning

confidence: 99%

An unsupervised online anomaly detection method for metal additive manufacturing processes via a statistical time-frequency domain algorithm

Chen,

Kopsaftopoulos,

Mishra

2023

Structural Health Monitoring

View full text Add to dashboard Cite

Anomalies often occur in metal additive manufacturing from processing inconsistencies and uncertainty. A robust fault detection system that uses sensor measurements such as melt pool imaging has the potential to improve part quality and save production time by anticipating print failure. Toward this goal, we develop and validate a fault detection technique using melt pool geometry-related measurements from an in situ near-infrared optical camera. This method is unsupervised and is trained on a small dataset, mitigating human error in classifying fault types, and reducing lead times for preparing training datasets. Furthermore, this method uses learned geometry-informed nominal behavior of the melt pool signal to make informed decisions on the process health. There are spatial-temporal characteristics embedded in the melt pool images, caused by the periodicity in the geometry-dependent raster pattern. These characteristics can be captured in the frequency domain using the signal spectrogram, a representation of the frequency content over time. Defects will appear in the spectrogram, disrupting the healthy spectral response. To quantify healthy spectrograms, we use principal component (PC) decomposition to extract the features of these spectrograms as a set of nominal basis vectors. Anomaly detection is then performed by calculating the error between the original and reconstructed spectrogram vector by projection of the spectrogram PCs onto the nominal basis. The reconstruction error for anomalous signals is larger than that from healthy signals, which is then used for fault detection. A one-tailed statistical test is used to determine the fault detection threshold for the reconstruction error signal. This method is tested on three raster patterns and performs better than a comparative time-series thresholding method. We demonstrate that this time-frequency algorithm can detect both temporal faults (which occur at a single time instant) and spatial faults (such as those introduced by an improper sintering), differentiating them from nominal operation.

show abstract

Multi phenomena melt pool sensor data fusion for enhanced process monitoring of laser powder bed fusion additive manufacturing

Cited by 34 publications

References 76 publications

Metal Laser-Based Powder Bed Fusion Process Development Using Optical Tomography

Metal Laser-Based Powder Bed Fusion Process Development Using Optical Tomography

Accelerating process development for 3D printing of new metal alloys

An unsupervised online anomaly detection method for metal additive manufacturing processes via a statistical time-frequency domain algorithm

Contact Info

Product

Resources

About