In-Situ Laser-Based Process Monitoring and In-Plane Surface Anomaly Identification for Additive Manufacturing Using Point Cloud and Machine Learning

Abstract

Additive Manufacturing (AM) is a trending technology with great potential in manufacturing. In-situ process monitoring is a critical part of quality assurance for AM process. Anomalies need to be identified early to avoid further deterioration of the part quality. This paper presents an in-situ laser-based process monitoring and anomaly identification system to assure fabrication quality of Fused Filament Fabrication (FFF) machine. The proposed data processing and communication architecture of the monitoring system establishes the data transformation between workstation, FFF machine, and laser scanner control system. The data processing performs calibration, filtering, and segmentation for the point cloud of each layer acquired from a 3D laser scanner during the fabrication process. The point cloud dataset with in-plane surface depth information is converted into a 2D depth image. Each depth image is discretized into 100 equal regions of interest and then labeled accordingly. Using the image dataset, four Machine Learning (ML) classification models are trained and compared, namely Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Convolutional Neural Network (CNN), and Hybrid Convolution AutoEncoder (HCAE). The HCAE classification model shows the best performance based on F-scores to effectively classify the in-plane anomalies into four categories, namely empty region, normal region, bulge region, and dent region.

The applications of nature‐inspired algorithms in Internet of Things‐based healthcare service: A systematic literature review

“…The inherent complexity of GA may hinder their real‐time applicability in dynamic healthcare environments where prompt decision‐making is crucial. Moreover, the lack of inherent interpretability in the solutions generated by GAs poses challenges in healthcare contexts that prioritize transparent and comprehensible decision‐making processes 92 . Balancing these challenges is pivotal to ensuring the effective integration of GA in IoT‐based healthcare services, addressing their limitations while leveraging their optimization capabilities for improved patient care and healthcare system efficiency 93 …”

“…Moreover, the lack of inherent interpretability in the solutions generated by GAs poses challenges in healthcare contexts that prioritize transparent and comprehensible decision-making processes. 92 Balancing these challenges is pivotal to ensuring the effective integration of GA in IoT-based healthcare services, addressing their limitations while leveraging their optimization capabilities for improved patient care and healthcare system efficiency. 93 So, the genetic algorithm procedure typically begins with setting the generation counter, starting from zero.…”

On-Machine LTS Integration for Layer-Wise Surface Quality Characterization in MEX/P

“…Although particularly popular in metal AM [21][22][23], layer-wise monitoring has also been applied in MEX/P, primarily through three different sensing technologies: thermal sensing [24], 2D vision [25,26], and 3D vision [16,23,[27][28][29][30][31][32][33][34][35][36][37][38][39][40]. Monitoring the 3D layer topography offers distinct advantages over thermal and two-dimensional sensing, as it allows for direct measurement of layer features, like layer height [27,28], or in-plane defects [16,23,30,31].…”

“…On the other hand, the characterization of surface texture requires a high-resolution LTS and has been mostly beyond the scope of research efforts in this field, although its usefulness has been explored in off-machine arrangements [29]. [36] Built in-house On-Machine Fixed to the structure N/A Layer contour [37] Keyence LJ-V7200 Off-Machine Independent structure with linear actuators 1 µm Warpage [38,40] Keyence LJ-V7200 Off-Machine Independent structure with linear actuators 1 µm…”

“…Monitoring the 3D layer topography offers distinct advantages over thermal and two-dimensional sensing, as it allows for direct measurement of layer features, like layer height [ 27 , 28 ], or in-plane defects [ 16 , 23 , 30 , 31 ]. Two technologies are mainly used for 3D monitoring of layer geometry: structured light photogrammetry [ 32 , 33 , 34 , 39 ] and laser triangulation (LT) [ 16 , 23 , 29 , 31 , 35 , 37 , 38 , 40 ]. Research endeavors employing structured light are challenged by the relatively low accuracy of such sensors.…”