26 July 2021 in IEEE Transactions on Automation Science and Engineering
Tensor data with rich structural information become increasingly important in process modeling, monitoring, and diagnosis in manufacturing medical and other applications. Here structural information is referred to the information of tensor components such as sparsity, smoothness, low-rank, and piecewise constancy. To reveal useful information from tensor data, we propose to decompose the tensor into the summation of multiple components based on their different structural information. In this article, we provide a new definition of structural information in tensor data. We then propose an additive tensor decomposition (ATD) framework to extract useful information from tensor data. This framework specifies a high dimensional optimization problem to obtain the components with distinct structural information. An alternating direction method of multipliers (ADMM) algorithm is proposed to solve it, which is highly parallelable and thus suitable for the proposed optimization problem. Two simulation examples and a real case study in medical image analysis illustrate the versatility and effectiveness of the ATD framework.
21 February 2022 in Journal of Manufacturing Science and Engineering
In a half fuselage assembly process, shape control is vital for achieving ultra-high-precision assembly. To achieve better shape adjustment, we need to determine the optimal location and force of each actuator to push or pull a fuselage to compensate for its initial shape distortion. The current practice achieves this goal by solving a surrogate model-based optimization problem. However, there are two limitations of this surrogate model-based method: (1) low efficiency: collecting training data for surrogate modeling from many finite element analysis (FEA) replications is time-consuming; (2) non-optimality: The required number of FEA replications for building an accurate surrogate model will increase as the potential number of actuator locations increases. Therefore, the surrogate model can only be built on a limited number of prespecified potential actuator locations, which will lead to suboptimal control results. To address these issues, this paper proposes an FEA model-based automatic optimal shape control (AOSC) framework. This method directly loads the system equation from the FEA simulation platform to determine the optimal location and force of each actuator. Moreover, the proposed method further integrates the cautious control concept into the AOSC system to address model uncertainties in practice. The case study with industrial settings shows that the proposed Cautious AOSC method achieves higher control accuracy compared to the current industrial practice.
24 August 2022 in IISE Transactions
This article proposes a general fixture layout design framework that directly integrates the system equation with the convex relaxation method. Note that the optimal fixture design problem is a large-scale combinatorial optimization problem; we relax it to a convex Semi-Definite Programming (SDP) problem by adopting sparse learning and SDP relaxation techniques. It can be solved efficiently by existing convex optimization algorithms and thus generates a near-optimal fixture layout. A real case study in the half-to-half fuselage assembly process indicates the superiority of our proposed algorithm compared to the current industry practice and state-of-art methods.
27 June 2025 in IEEE Transactions on Automation Science and Engineering
Defect segmentation is crucial for quality control in advanced manufacturing, yet data scarcity poses challenges for state-of-the-art supervised deep learning. Synthetic defect data generation is a popular approach for mitigating data challenges. However, many current methods simply generate defects following a fixed set of rules, which may not directly relate to downstream task performance. This can lead to suboptimal performance and may even hinder the downstream task. To solve this problem, we leverage a novel bi-level optimization-based synthetic defect data generation framework. We use an online synthetic defect generation module grounded in the commonly-used Cut&Paste framework, and adopt an efficient gradient-based optimization algorithm to solve the bi-level optimization problem. We achieve simultaneous training of the defect segmentation network, and learn various parameters of the data synthesis module by maximizing the validation performance of the trained defect segmentation network. Our experimental results on benchmark datasets under limited data settings show that the proposed bi-level optimization method can be used for learning the most effective locations for pasting synthetic defects thereby improving the segmentation performance by up to 21.3% when compared to pasting defects at random locations. We also demonstrate up to 2.7% performance gain by learning the importance weights for different augmentation-specific defect data sources when compared to giving equal importance to all the data sources.
30 October 2024 in IISE Transactions