Farbod Khameneifar

Point cloud processing of raw scan data is a critical step to enhance the accuracy and efficiency in computer-aided inspection and remanufacturing of damaged aero-engine blades. This paper presents a new methodology to obtain a noise-reduced and simplified dataset from the raw scan data while preserving the underlying geometry of the damaged blade in high-curvature and damaged regions. At first, outliers are removed from the scan data, and measurement noise is reduced through local least-squares quadric surface/plane fitting on the adaptive support domain of measured points under the measurement uncertainty constraint of inspection data. Then, a directed Hausdorff distance-based region growing scheme is developed to progressively search within the support domain of denoised data points to obtain a down-sampled dataset while preserving the local geometric shape of the surface. Numerical and experimental case studies have been conducted to evaluate the accuracy and computation time of scan-to-CAD rigid registration and CAD-to-scan non-rigid registration processes using the down-sampled dataset of damaged blades. The results have demonstrated that the proposed methodology effectively removes the measurement noise and outliers and provides a down-sampled dataset from the scan data that can significantly reduce the time complexity of the computer-aided inspection and remanufacturing process of the point cloud of damaged blades with a negligible loss of accuracy.

As Additive Manufacturing (AM) evolves from prototyping to full-scale production, improving geometric accuracy becomes increasingly critical, especially for applications requiring high dimensional fidelity. This study proposes a machine learning-based approach to enhance the geometric accuracy of 3D printed parts produced by Fused Filament Fabrication (FFF), a widely used material extrusion process in which thermoplastic filament is heated and deposited layer by layer to form a part. Our method relies on a Convolutional Neural Network (CNN) trained to predict a systematic deviation field based on 3D scan data of a sacrificial print. These scans are acquired using a structured light 3D scanner, which provides detailed surface information on geometric deviations that arise during the printing process. The predicted deviation field is then inverted and applied to the digital model to generate a compensated geometry, which, when printed, offsets the errors observed in the original part. Experimental validation using a complex reference geometry shows that the proposed compensation method achieves an 88.5% reduction in mean absolute geometric deviation compared to the uncompensated print. This significant improvement underscores the CNN’s ability to generalize across geometric features and capture systematic deformation patterns inherent to FFF. The results demonstrate the potential of combining 3D scanning and deep learning to enable adaptive, data-driven compensation strategies in AM. The method proposed in this paper contributes to reducing trial-and-error iterations, improving part quality, and facilitating the broader adoption of FFF for precision-demanding industrial applications.

Background: AI-enabled digital twins (DTs) are advanced virtual models of a complex real-world system, augmented with predictive AI capabilities, which have a potential for transforming healthcare and clincial decision making. Despite the growing interest and need in such DTs, the literature lacks a unified framework for its development and implementation. Objective: This study aims to map the existing knowledge on AI-enabled DTs for clinical decision-making, and develop a comprehensive framework for its development and implementation. Methods: Informed by the scoping review frameworks established by Arksey and O'Malley, and the Joanna Briggs Institute, we performed a scoping review of studies reporting on the development and implementation of AI-enabled DTs for clinical decision-making in any healthcare setting. The search strategy was developed by a professional academic librarian for three databases, i.e., PubMed, Embase (Ovid), and IEEE Xplore, from the date of inception until August 2023. We also conducted a grey literature search on Google Scholar. Moreover, we scanned the references of all included studies to identify additional potentially relevant studies for inclusion. A reviewer screened titles and abstracts, full-text articles, and charted data, and the second reviewer verified them. Data were summarised descriptively using content analysis. Key steps in DTs development were identified and combined to create the DECIDE-Twin framework. Results: Out of 421 records, 11 were included: seven reviews and four empirical studies, all published from 2020 onward. The reviews contained either a framework or information that was used to construct our newly developed framework. The empirical studies reported the development of DTs, and one reported a common infrastructure for a wide range of applications for DTs. Conclusion: We developed the DECIDE-Twin framework that could serve as a guide for researchers and practitioners for the development and implementation of AI-enabled DTs in clinical decision making. Further research is needed to validate and implement this framework across various use cases.

This paper proposes the use of a pseudo-3D ball-lattice artifact to characterize a handheld laser scanner from a metrological standpoint. The artifact allows the computation of local and global errors in measurement by using the reference-frame-independent parameters of size, form, and distance within the measuring volume of the scanner, and in a single point cloud, without the need for registration. A set of tests was performed using the whole measuring volume, and three acquisition parameters, namely the orientation of the sweeps during the scans, the exposure time, and the distance to the scanner were analyzed for their effects on the accuracy of the scan data. A composite error including the errors in measuring size, form, and distance was used as a single figure of merit to characterize the performance of the scanner in relation to the data-acquisition parameters. The orientation of sweeps did not have a considerable effect on the errors. The accuracy of the scan data was strongly affected by exposure time and its interaction with the distance at which the artifact was scanned. The errors followed a quadratic trend with respect to the distance of the artifact to the scanner. The tested scanner performed best at its manufacturer’s recommended stand-off distance.

Airfoil blades are typically inspected in sections to verify their conformance to the geometric tolerances specified on their nominal design. To maintain the accuracy of geometric error evaluation, in particular, for the position and orientation errors of the airfoil sections, sectional airfoil profiles should be reconstructed from the inspection data points. This paper presents a new method to automatically reconstruct the airfoil profile from unorganized noisy sectional data points of 3D scanned blades. A three-step airfoil profile reconstruction approach is presented. First, the algorithm thins the scattered set of sectional data points by projecting them onto the local curves fitted to them. For this purpose, a recursive weighted local least-squares scheme is proposed to fit local curves within the measurement uncertainty constraint of inspection data. Then, to order the thinned set of data points, the profile polygon is generated and imperfect nodes are modified by evaluation of the angular deviation of edges. Finally, a closed nonperiodic B-spline curve is fitted to the thinned and ordered set of data points to construct the smooth airfoil profile. A series of case studies have been carried out to demonstrate the effectiveness of the proposed airfoil profile reconstruction method. Implementation results have demonstrated that the proposed method is accurate and robust to noise. In addition to blade inspection, other applications such as repair and adaptive machining of aero-engine blades can equally benefit from the proposed method for automatic airfoil profile reconstruction.

This paper presents a novel method for aligning the scanned point clouds of damaged blades with their nominal computer-aided design (CAD) model. To inspect a damaged blade, the blade surface is scanned and the scan data in the form of a point cloud is compared with the nominal CAD model of the blade. To be able to compare the scanned point cloud and the CAD model, they must be brought to a common coordinate system via a registration algorithm. The geometric nonconformity between the scanned damaged blade and its nominal model stemmed from the damaged regions can affect the registration (alignment) outcome. The alignment errors then cause wrong inspection results. To prevent this from happening, the data points from the damaged regions have to be removed from the alignment calculations. The proposed registration method in this work can accurately and automatically eliminate the unreliable scanned data points of the damaged regions from the registration process. The main feature is a correspondence search technique based on the geometric properties of the local neighborhood of points. By combining the average curvature Hausdorff distance and average Euclidean Hausdorff distance, a metric is defined to locally measure the dissimilarities between the scan data and the nominal model and progressively remove the identified unreliable data points of the damaged regions with each iteration of the fine-tuned alignment algorithm. Implementation results have demonstrated that the proposed method is accurate and robust to noise with superior performance in comparison with the existing methods.