An official website of the United States government
The use of computer-aided manufacturing (CAM) software is essential in the rapid production of high-quality computer numerical control (CNC) machining toolpaths for complex parts. Typical CAM software relies on analytical representations of part geometry, where curves and surfaces are described by parametric functions. This paper proposes the use of a novel way to represent part geometry known as a voxel model. A voxel model uses a three-dimensional array of small cubes to represent a part volume; these cubes, or voxels, are the three-dimensional analog of two-dimensional pixels in an image. The use of voxels for a CAM application enables higher surface complexity, simplified collision checking, and more robust analysis of material removal than would be possible with typical parametric CAM. The unique capabilities of the voxel-based CAM approach described in this paper enable rapid production of high-quality 5-axis toolpaths for machining complex parts, such as the centrifugal compressor assembly that is presented in this work.
more »
« less
Deep learning-based semantic segmentation of machinable volumes for cyber manufacturing service
Enabling the vision of on-demand cyber manufacturing-as-a-service requires a new set of cloud-based computational tools for design manufacturability feedback and process selection to connect designers with manufacturers. In our prior work, we demonstrated a generative modeling approach in voxel space to model the shape transformation capabilities of machining operations using unsupervised deep learning. Combining this with a deep metric learning model enabled quantitative assessment of the manufacturability of a query part. In this paper, we extend our prior work by developing a semantic segmentation approach for machinable volume decomposition using pre-trained generative process capability models, which output per-voxel manufacturability feedback and labels of candidate machining operations for a query 3D part. Using three types of complex parts as case studies, we show that the proposed method accurately identifies machinable and non-machinable volumes with an average intersection-over-union (IoU) of 0.968 for axisymmetric machining operations, and a class-average F1 score of 0.834 for volume segmentation by machining operation.
more »
« less
- PAR ID:
- 10502805
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Journal of Manufacturing Systems
- Volume:
- 72
- Issue:
- C
- ISSN:
- 0278-6125
- Page Range / eLocation ID:
- 16 to 25
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Medical image analysis using deep learning has recently been prevalent, showing great performance for various downstream tasks including medical image segmentation and its sibling, volumetric image segmentation. Particularly, a typical volumetric segmentation network strongly relies on a voxel grid representation which treats volumetric data as a stack of individual voxel `slices', which allows learning to segment a voxel grid to be as straightforward as extending existing image-based segmentation networks to the 3D domain. However, using a voxel grid representation requires a large memory footprint, expensive test-time and limiting the scalability of the solutions. In this paper, we propose Point-Unet, a novel method that incorporates the eciency of deep learning with 3D point clouds into volumetric segmentation. Our key idea is to rst predict the regions of interest in the volume by learning an attentional probability map, which is then used for sampling the volume into a sparse point cloud that is subsequently segmented using a point-based neural network. We have conducted the experiments on the medical volumetric segmentation task with both a small-scale dataset Pancreas and large-scale datasets BraTS18, BraTS19, and BraTS20 challenges. A comprehensive benchmark on di erent metrics has shown that our context-aware Point-Unet robustly outperforms the SOTA voxel-based networks at both accuracies, memory usage during training, and time consumption during testing.more » « less
-
Abstract Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-training, offers promise for few-shot learning, aiding in manufacturability tasks where data can be limited. This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder. The pretrained model is evaluated across four manufacturability indicators obtained from CAM simulations: subtractive machining (SM) time, additive manufacturing (AM) time, residual von Mises stress, and blade collisions during Laser Power Bed Fusion process. Across all case studies, the model pre-trained by VIRL shows substantial enhancements in generalizability, as measured by R2 regression results, with improved performance on limited data and superior predictive accuracy with larger datasets. Regarding deployment strategy, case-specific phenomenon exists where finetuning VIRL-pretrained models adversely affects AM tasks with limited data but benefits SM time prediction. Moreover, the efficacy of Low-rank adaptation (LoRA), which balances between probing and finetuning, is explored. LoRA shows stable performance akin to probing with limited data, while achieving a higher upper bound than probing as data size increases, without the computational costs of finetuning. Furthermore, static normalization of manufacturing indicators consistently performs well across tasks, while dynamic normalization enhances performance when a reliable task dependent input is available.more » « less
-
Abstract Deep generative learning cannot only be used for generating new data with statistical characteristics derived from input data but also for anomaly detection, by separating nominal and anomalous instances based on their reconstruction quality. In this paper, we explore the performance of three unsupervised deep generative models—variational autoencoders (VAEs) with Gaussian, Bernoulli, and Boltzmann priors—in detecting anomalies in multivariate time series of commercial-flight operations. We created two VAE models with discrete latent variables (DVAEs), one with a factorized Bernoulli prior and one with a restricted Boltzmann machine (RBM) with novel positive-phase architecture as prior, because of the demand for discrete-variable models in machine-learning applications and because the integration of quantum devices based on two-level quantum systems requires such models. To the best of our knowledge, our work is the first that applies DVAE models to anomaly-detection tasks in the aerospace field. The DVAE with RBM prior, using a relatively simple—and classically or quantum-mechanically enhanceable—sampling technique for the evolution of the RBM’s negative phase, performed better in detecting anomalies than the Bernoulli DVAE and on par with the Gaussian model, which has a continuous latent space. The transfer of a model to an unseen dataset with the same anomaly but without re-tuning of hyperparameters or re-training noticeably impaired anomaly-detection performance, but performance could be improved by post-training on the new dataset. The RBM model was robust to change of anomaly type and phase of flight during which the anomaly occurred. Our studies demonstrate the competitiveness of a discrete deep generative model with its Gaussian counterpart on anomaly-detection problems. Moreover, the DVAE model with RBM prior can be easily integrated with quantum sampling by outsourcing its generative process to measurements of quantum states obtained from a quantum annealer or gate-model device.more » « less
-
Spectrum cartography (SC) techniques craft multi-domain (e.g., space and frequency) radio maps from limited measurements, which is an ill-posed inverse problem. Recent works used low-dimensional priors such as a low tensor rank structure and a deep generative model to assist radio map estimation---with provable guarantees. However, a premise of these approaches is that the sensors are able to send real-valued feedback to a fusion center for SC---yet practical communication systems often use (heavy) quantization for signaling. This work puts forth a limited feedback-based SC framework. Similar to a prior work, a generative adversarial network (GAN)-based deep prior is used in our framework for fending against heavy shadowing. However, instead of using real-valued feedback, a random quantization strategy is adopted and a maximum likelihood estimation (MLE) criterion is proposed. Analysis shows that the MLE provably recovers the radio map, under reasonable conditions. Simulations are conducted to showcase the effectiveness of the proposed approach.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1016/j.jmsy.2023.11.005
