Xisong Dong

Laser powder bed fusion (LPBF) is an additive manufacturing process capable of producing intricate structures with high accuracy. Despite this capability, it struggles to achieve the required reliability for mass production—specifically the stability of a production run and repeatability across multiple runs. Parameter optimization, which adjusts process parameters to regulate a specific quantity of interest (QoI), is a crucial means of quality control. Existing methods, however, have not adequately addressed both random and systematic factors in the LPBF process. The stochastic nature of the process is often neglected under the assumption that identical parameter inputs will consistently yield the same QoI. This deviates from reality and is not intended to reduce potential variations in the QoI. Moreover, many studies do not incorporate the systematic neighboring effects between scan tracks into their optimization, so process reliability cannot be guaranteed. To address this issue, this study focuses on optimizing the probability distribution of the QoI. The key idea is not only to increase the likelihood of achieving the ideal QoI but also to reduce its variance. This is achieved by uncertainty-aware modeling and optimization of the LPBF process using machine learning. Specifically, the problem is formulated as maximizing the posterior distribution of scan parameters given an ideal QoI sequence and historical manufacturing data, yielding a large-scale constrained optimization problem. A stochastic, distributed, gradient-based method is proposed to solve this problem, where a coarse-to-fine strategy plays a critical role in accelerating convergence. A case study is then conducted to stabilize the melt pool volume by optimizing laser powers. The solutions are verified in a calibrated finite element-based simulation environment, in which the variations of the melt pool volume are effectively reduced both within a single run and across multiple runs. The implementation of our method is available at https://github.com/qihangGH/uncertainty_aware_param_optim_for_AM.

Digital light processing (DLP) is a popular additive manufacturing technology that uses light irradiation to fabricate 3-D devices via a projector to achieve laser-sensitive resin curing. However, the performance and reliability of DLP can be affected by internal defects such as printing errors and the accumulation of residual stress. Existing defect detection methods rely on monitoring the printed parts, which leads to resource wastage and struggles to effectively handle imbalanced defect data. In this article, we propose a defect detection method called dual neural network, which involves detecting defects in materials before the printing process to prevent resource wastage and serious consequences. Specifically, to handle the highly imbalanced class distribution problem in online DLP defect detection, dual neural network utilizes a domain learner and balance learner to effectively balance the information of the minority class and learn the generalization knowledge from the imbalanced defect dataset. Experimental results demonstrate the effectiveness of our proposed method, which has also been applied to real-world production equipment successfully.

The quality of the dataset is critical to the performance of neural networks for error prediction in 3-D printing. In order to enlarge the dataset, we propose a customized two-stage framework, cascaded cross-modality generative adversarial networks (CCMGANs), for generating dental crown meshes in an unsupervised manner. At the first stage, a displacement map-guided generative adversarial network (GAN) is used to generate coarse meshes with diverse shapes. At the second stage, fine-grained details are added to the coarse meshes using an image-based GAN. Unlike previous work that integrates a differentiable renderer into the mesh deformation process directly, we adopt a two-step strategy. First, we use a depth image refinement module to achieve the domain transformation from the rendered depth images of the generated meshes to those of the real ones. Then, we propose a mesh refinement module to optimize the coarse meshes in an image-supervised manner. To alleviate the self-intersection problem, we propose a loss to penalize the distances of point pairs in self-intersection regions. Experimental results show that our method is able to generate highly realistic meshes and outperforms the state-of-the-art point cloud generation method TreeGCN in terms of the metrics FDD, MMD-CD, MMD-EMD, and COV-EMD. Furthermore, we utilize the generated data to augment the original dataset, and demonstrate that the generated data can effectively improve the accuracy of the error prediction task in 3-D printing.

Additive manufacturing (AM) is gaining prominence across numerous fields, which involves the generation of extensive data at each process stage. A relational database is a useful tool to store such AM data and streamline data retrieval. Users can specify the value of one AM variable or attribute and retrieve the corresponding record values of another attribute. This establishes the correlations between AM variables, and supports applications such as process planning. Nonetheless, such an operation is a “hard” query, which lacks reasoning capabilities and fails to provide useful information when required records are missing. It is urgent to develop a more powerful AM database to handle AM data better, which should support “soft” queries, be scalable to high-dimensional data, and maintain flexible query functionality among multiple attributes. In this paper, we construct an AM database with probabilistic modeling and transformation-invariant feature learning, which is termed as a probabilistic AM database (PAMDB). The PAMDB allows the selection of any AM attribute as a query attribute, or even multiple attributes as query attributes, to retrieve the values of other attributes, which is adapted to unseen, high-dimensional, and multimodal AM data. Two case studies were conducted for laser powder bed fusion (LPBF) and vat photopolymerization (VP). Compared with existing methods, experimental results underscore the efficacy of the PAMDBs, both qualitatively and quantitatively, in tasks that includes melt pool size prediction and scan parameter estimation in LPBF, and defect detection for the resin deposition process in VP.

This article proposes a parallel flexible manufacturing system (FMS), which is divided into three subparallel systems, including a parallel manufacturing system, a parallel inspection system, and a parallel loading–unloading system. By building a chess parallel manufacturing production line, the lightweight practice of a parallel FMS is completed. Based on the parallel system ACP idea, the parallel FMS can realize the agility advantage of flexible manufacturing to quickly respond to diverse needs; realize the ability to quickly correct defective products; and predict and optimize the production process through the analysis and modeling of production data, reducing the product quality defect rate. This article also proposes the concept of parallel flexible manufacturing triplets, adding a microphysical world to the artificial world and the physical world, highlighting the rapid iteration characteristics of flexible manufacturing.

As a typical biochemical treatment method, the activated sludge is used in various wastewater treatments. Activated wastewater treatment process is hard to control because of the complex nonlinear behavior, however, the stability of dissolved oxygen concentration (DOC) in the reaction tank is related to the quality and efficiency of processing. In this paper, a parallel wastewater treatment system based on the parallel intelligence theory is proposed to deal with the time-varying, nonlinear, and delay in the wastewater treatment process. Besides, computational experiments are designed and conducted to explore and verify the control strategy, which will guide the actual process through virtual and real interaction, so as to adapt to the complex and changeable wastewater treatment environment.