Hyperspectral imaging for prediction of surface roughness in laser powder bed fusion

Abstract

This article discusses the relevance of in situ quality assurance in metal additive manufacturing for cost-efficient product qualification. It presents an approach for monitoring the laser powder bed fusion (LPBF) process using an area-scan hyperspectral camera to predict the surface roughness Rz with the help of a convolutional neural network. These investigations were carried out during LPBF processing of the magnesium alloy WE43 that, due to its bioresorbability and compatibility, holds significant potential for biomedical implants. A data acquisition and processing methodology has been set up to enable efficient management of the hyperspectral data. The hyperspectral images obtained from the process were labeled with the surface roughness Rz as determined by a confocal microscope. The data was used to train a convolutional neural network whose hyperparameters were optimized in a hyperparameter tuning process. The resulting network was able to predict the surface roughness within a mean absolute error (MAE) of 4.1 μm over samples from three different parameter sets. Since this is significantly smaller than the spread of the actual roughness measured (MAE = 14.3 μm), it indicates that the network identified features in the hyperspectral data linking to the roughness. These results provide the basis for future research aiming to link hyperspectral process images to further part properties relevant for quality assurance.

A Survey of Image-Based Fault Monitoring in Additive Manufacturing: Recent Developments and Future Directions

“…It captures images across multiple spectral bands, allowing for detailed analysis and characterization of materials based on their spectral properties. It was used by [ 58 ] to inspect the surface roughness of printed materials. A 3D scanning coordinate-measuring machine (CMM) is a specialized device that combines the capabilities of a traditional CMM with 3D scanning technology.…”

“…CNNs have demonstrated remarkable performance in identifying various types of faults, including voids, porosity, cracks, and surface irregularities. Specifically, [ 21 , 26 , 30 , 31 , 32 , 35 , 37 , 39 , 40 , 41 , 43 , 44 , 46 , 47 , 50 , 52 , 55 , 58 , 60 , 61 , 71 , 72 ] used CNN or a CNN-based algorithm. CNN is commonly used in this application due to its ability to learn spatial hierarchies of features.…”

Safety Monitoring Method of Underground Pipeline based on Machine Learning and Parameter Statistics

“…Therefore, during the planning and design of urban pipelines, the development space should be reserved as much as possible for the pipelines that may be added in the future; the underground pipeline shall be laid under the green belt, sidewalk or non-motor vehicle lane of the road as far as possible according to the layout location requirements. When the layout space is limited, the pipeline with relatively few maintenance times and deep burial depth can be laid under the ground of the motor vehicle lane, and the area where vehicles frequently pass shall be avoided as far as possible; Comply with the requirements of horizontal clear distance When conducting the comprehensive horizontal layout of UP, ensure that the horizontal distance between pipelines and between pipelines and buildings (structures) meet the requirements of relevant specifications [5][6].…”

Dilated Spectral–Spatial Gaussian Transformer Net for Hyperspectral Image Classification

“…In addition to offering a wide area for the advancement of hyperspectral image (HSI) classification study, the diverse and rich methods of acquiring hyperspectral data also present new problems and opportunities for our comprehension and use of hyperspectral data. HSIs are currently used in several industries, including food safety [1,2], medical diagnostics [3], industrial product quality inspection [4], mineral detection [5], and pest and disease monitoring [6]. A wide range of topics, including noise removal [7], spectrum unmixing [8], data classification and clustering [9], and target identification and recognition [10,11], have been covered by the rich and varied development of HSI processing approaches.…”