paper_authors: M. Rahmani Dehaghani, Atieh Sahraeidolatkhaneh, Morgan Nilsen, Fredrik Sikström, Pouyan Sajadi, Yifan Tang, G. Gary Wang for: This paper focuses on developing a parameter-signature-property modeling and control approach to enhance the quality of additively manufactured parts using hot-wire directed energy deposition with a laser beam (DED-LB/w).methods: The paper employs a dynamic modeling approach to investigate the relationship between process parameters and melt pool width, as well as a fully connected artificial neural network to predict the final part property (bead width) based on melt pool signatures.results: The proposed parameter-signature-property modeling approach shows clear advantages in controlling the width of the part compared to a control loop with only process signature (melt pool width) information. The approach has the potential to be applied to control other part properties that cannot be directly measured or monitored in situ.Abstract
Hot-wire directed energy deposition using a laser beam (DED-LB/w) is a method of metal additive manufacturing (AM) that has benefits of high material utilization and deposition rate, but parts manufactured by DED-LB/w suffer from a substantial heat input and undesired surface finish. Hence, monitoring and controlling the process parameters and signatures during the deposition is crucial to ensure the quality of final part properties and geometries. This paper explores the dynamic modeling of the DED-LB/w process and introduces a parameter-signature-property modeling and control approach to enhance the quality of modeling and control of part properties that cannot be measured in situ. The study investigates different process parameters that influence the melt pool width (signature) and bead width (property) in single and multi-layer beads. The proposed modeling approach utilizes a parameter-signature model as F_1 and a signature-property model as F_2. Linear and nonlinear modeling approaches are compared to describe a dynamic relationship between process parameters and a process signature, the melt pool width (F_1). A fully connected artificial neural network is employed to model and predict the final part property, i.e., bead width, based on melt pool signatures (F_2). Finally, the effectiveness and usefulness of the proposed parameter-signature-property modeling is tested and verified by integrating the parameter-signature (F_1) and signature-property (F_2) models in the closed-loop control of the width of the part. Compared with the control loop with only F_1, the proposed method shows clear advantages and bears potential to be applied to control other part properties that cannot be directly measured or monitored in situ.
摘要
热束导电能量沉积使用激光束(DED-LB/w)是一种金属添加生产(AM)的方法，它具有高材料利用率和沉积速率的优点，但是制造出来的部件受到了大量的热输入和不想要的表面镀层。因此，对沉积过程参数和特征的监测和控制是至关重要，以确保最终部件的性能和几何尺寸。本文研究了DED-LB/w процесс的动态模型化，并提出了参数-特征-性能模型控制方法，以提高模型和控制不可直接测量或监测的部件性能的能力。研究表示，不同的处理参数对沉积过程中的溶融池宽度（特征）和束宽度（性能）的影响。对于单层和多层束，提出了参数-特征模型和特征-性能模型两种模型方法。使用全连接人工神经网络模型和预测最终部件性能，基于溶融池特征。最后，通过将参数-特征模型和特征-性能模型在关闭控制 loop中集成，证明了提posed方法的效iveness和实用性。相比只使用参数-特征模型控制 loop，提posed方法显示了明显的优势，并可以应用于控制其他不可直接测量或监测的部件性能。
Denoising total scattering data using Compressed Sensing
results: 该论文表明，通过使用压缩感知技术，可以将单个Diffraction测量转化为一个有效无限多的虚拟测量，从而实现超分辨率成像。Abstract
To obtain the best resolution for any measurement there is an ever-present challenge to achieve maximal differentiation between signal and noise over as fine of sampling dimensions as possible. In diffraction science these issues are particularly pervasive when analyzing small crystals, systems with diffuse scattering, or other systems in which the signal of interest is extremely weak and incident flux and instrument time is limited. We here demonstrate that the tool of compressed sensing, which has successfully been applied to photography, facial recognition, and medical imaging, can be effectively applied to diffraction images to dramatically improve the signal-to-noise ratio (SNR) in a data-driven fashion without the need for additional measurements or modification of existing hardware. We outline a technique that leverages compressive sensing to bootstrap a single diffraction measurement into an effectively arbitrary number of virtual measurements, thereby providing a means of super-resolution imaging.
摘要
results: 通过使用开源的 Samsung S7 ISP 和 MIT-Adobe FiveK 数据集，实现了高达 99.6% 的检测精度，False Positives 低于 0.6%，并在 70% 损害的图像中实现了平均像素误差在 1.5% 之间的修复。Abstract
Efficient and effective on-line detection and correction of bad pixels can improve yield and increase the expected lifetime of image sensors. This paper presents a comprehensive Deep Learning (DL) based on-line detection-correction approach, suitable for a wide range of pixel corruption rates. A confidence calibrated segmentation approach is introduced, which achieves nearly perfect bad pixel detection, even with few training samples. A computationally light-weight correction algorithm is proposed for low rates of pixel corruption, that surpasses the accuracy of traditional interpolation-based techniques. We also propose an autoencoder based image reconstruction approach which alleviates the need for prior bad pixel detection and yields promising results for high rates of pixel corruption. Unlike previous methods, which use proprietary images, we demonstrate the efficacy of the proposed methods on the open-source Samsung S7 ISP and MIT-Adobe FiveK datasets. Our approaches yield up to 99.6% detection accuracy with <0.6% false positives and corrected images within 1.5% average pixel error from 70% corrupted images.
摘要
高效和有效的在线检测和修正坏像素可以提高图像传感器的产量和预期的寿命。这篇论文提出了一种基于深度学习（DL）的全面在线检测修正方法，适用于各种坏像素损害率。我们引入了一种决度规则化的分割方法，可以在少量训练样本下达到几乎完美的坏像素检测效果。我们还提出了一种 Computational 轻量级的修正算法，可以在低坏像素率下超越传统的 interpolate-based 技术。此外，我们还提出了一种基于 autoencoder 的图像重建方法，可以消除先前的坏像素检测，并且在高坏像素率下实现了出色的 результаados。与先前的方法不同，我们使用开源的 Samsung S7 ISP 和 MIT-Adobe FiveK 数据集来证明方法的可行性。我们的方法可以达到 99.6% 的检测精度，False Positives <0.6%，并且在 70% 损害的图像上修正了 <1.5% 的平均像素误差。