arXiv subjects

Levent Burak Kara

Publications and source records attributed to Levent Burak Kara.

At least 37 records · Page 2Linked to original sources

arXiv2023

Inference of highly time-resolved melt pool visual characteristics and spatially-dependent lack-of-fusion defects in laser powder bed fusion using acoustic and thermal emission data

With a growing demand for high-quality fabrication, the interest in real-time process and defect monitoring of laser powder bed fusion (LPBF) has increased, leading manufacturers to incorporate a variety of online sensing methods including acoustic sensing, photodiode sensing, and high-speed imaging. However, real-time acquisition of high-resolution melt pool images in particular remains computationally demanding in practice due to the high variability of melt pool morphologies and the limitation of data caching and transfer, making it challenging to detect the local lack-of-fusion (LOF) defect occurrences. In this work, we propose a new acoustic and thermal information-based monitoring method that can robustly infer critical LPBF melt pool morphological features in image forms and detect spatially-dependent LOF defects within a short period. We utilize wavelet scalogram matrices of acoustic and photodiode clip data to identify and predict highly time-resolved (within a 1.0 ms window) visual melt pool characteristics via a well-trained data-driven pipeline. With merely the acoustic and photodiode-collected thermal emission data as the input, the proposed pipeline enables data-driven inference and tracking of highly variable melt pool visual characteristics with $R^2=0.8$. We subsequently validate our proposed approach to infer local LOF defects between two adjacent scanlines, showing that our proposed approach can outperform our selected baseline theoretical model based on previous literature. Revealing the physical correlation between airborne acoustic emission, thermal emission, and melt pool morphology, our work demonstrates the feasibility of creating an efficient and cost-effective acoustic- and thermal-based approach to facilitate online visual melt pool characterization and LOF defect detection.

physics.app-ph↗

arXiv2023

Curve-based Neural Style Transfer

This research presents a new parametric style transfer framework specifically designed for curve-based design sketches. In this research, traditional challenges faced by neural style transfer methods in handling binary sketch transformations are effectively addressed through the utilization of parametric shape-editing rules, efficient curve-to-pixel conversion techniques, and the fine-tuning of VGG19 on ImageNet-Sketch, enhancing its role as a feature pyramid network for precise style extraction. By harmonizing intuitive curve-based imagery with rule-based editing, this study holds the potential to significantly enhance design articulation and elevate the practice of style transfer within the realm of product design.

cs.CV↗

arXiv2023

DMF-TONN: Direct Mesh-free Topology Optimization using Neural Networks

We propose a direct mesh-free method for performing topology optimization by integrating a density field approximation neural network with a displacement field approximation neural network. We show that this direct integration approach can give comparable results to conventional topology optimization techniques, with an added advantage of enabling seamless integration with post-processing software, and a potential of topology optimization with objectives where meshing and Finite Element Analysis (FEA) may be expensive or not suitable. Our approach (DMF-TONN) takes in as inputs the boundary conditions and domain coordinates and finds the optimum density field for minimizing the loss function of compliance and volume fraction constraint violation. The mesh-free nature is enabled by a physics-informed displacement field approximation neural network to solve the linear elasticity partial differential equation and replace the FEA conventionally used for calculating the compliance. We show that using a suitable Fourier Features neural network architecture and hyperparameters, the density field approximation neural network can learn the weights to represent the optimal density field for the given domain and boundary conditions, by directly backpropagating the loss gradient through the displacement field approximation neural network, and unlike prior work there is no requirement of a sensitivity filter, optimality criterion method, or a separate training of density network in each topology optimization iteration.

cs.CE↗

arXiv2023

Automating Style Analysis and Visualization With Explainable AI -- Case Studies on Brand Recognition

Incorporating style-related objectives into shape design has been centrally important to maximize product appeal. However, stylistic features such as aesthetics and semantic attributes are hard to codify even for experts. As such, algorithmic style capture and reuse have not fully benefited from automated data-driven methodologies due to the challenging nature of design describability. This paper proposes an AI-driven method to fully automate the discovery of brand-related features. Our approach introduces BIGNet, a two-tier Brand Identification Graph Neural Network (GNN) to classify and analyze scalar vector graphics (SVG). First, to tackle the scarcity of vectorized product images, this research proposes two data acquisition workflows: parametric modeling from small curve-based datasets, and vectorization from large pixel-based datasets. Secondly, this study constructs a novel hierarchical GNN architecture to learn from both SVG's curve-level and chunk-level parameters. In the first case study, BIGNet not only classifies phone brands but also captures brand-related features across multiple scales, such as the location of the lens, the height-width ratio, and the screen-frame gap, as confirmed by AI evaluation. In the second study, this paper showcases the generalizability of BIGNet learning from a vectorized car image dataset and validates the consistency and robustness of its predictions given four scenarios. The results match the difference commonly observed in luxury vs. economy brands in the automobile market. Finally, this paper also visualizes the activation maps generated from a convolutional neural network and shows BIGNet's advantage of being a more human-friendly, explainable, and explicit style-capturing agent. Code and dataset can be found on Github: 1. Phone case study: github.com/parksandrecfan/bignet-phone 2. Car case study: github.com/parksandrecfan/bignet-car

cs.CV↗

arXiv2023

Topology Optimization using Neural Networks with Conditioning Field Initialization for Improved Efficiency

We propose conditioning field initialization for neural network based topology optimization. In this work, we focus on (1) improving upon existing neural network based topology optimization, (2) demonstrating that by using a prior initial field on the unoptimized domain, the efficiency of neural network based topology optimization can be further improved. Our approach consists of a topology neural network that is trained on a case by case basis to represent the geometry for a single topology optimization problem. It takes in domain coordinates as input to represent the density at each coordinate where the topology is represented by a continuous density field. The displacement is solved through a finite element solver. We employ the strain energy field calculated on the initial design domain as an additional conditioning field input to the neural network throughout the optimization. The addition of the strain energy field input improves the convergence speed compared to standalone neural network based topology optimization.

cs.LG↗

arXiv2023

Component Segmentation of Engineering Drawings Using Graph Convolutional Networks

We present a data-driven framework to automate the vectorization and machine interpretation of 2D engineering part drawings. In industrial settings, most manufacturing engineers still rely on manual reads to identify the topological and manufacturing requirements from drawings submitted by designers. The interpretation process is laborious and time-consuming, which severely inhibits the efficiency of part quotation and manufacturing tasks. While recent advances in image-based computer vision methods have demonstrated great potential in interpreting natural images through semantic segmentation approaches, the application of such methods in parsing engineering technical drawings into semantically accurate components remains a significant challenge. The severe pixel sparsity in engineering drawings also restricts the effective featurization of image-based data-driven methods. To overcome these challenges, we propose a deep learning based framework that predicts the semantic type of each vectorized component. Taking a raster image as input, we vectorize all components through thinning, stroke tracing, and cubic bezier fitting. Then a graph of such components is generated based on the connectivity between the components. Finally, a graph convolutional neural network is trained on this graph data to identify the semantic type of each component. We test our framework in the context of semantic segmentation of text, dimension and, contour components in engineering drawings. Results show that our method yields the best performance compared to recent image, and graph-based segmentation methods.

cs.CV↗

arXiv2023

Target specific peptide design using latent space approximate trajectory collector

Despite the prevalence and many successes of deep learning applications in de novo molecular design, the problem of peptide generation targeting specific proteins remains unsolved. A main barrier for this is the scarcity of the high-quality training data. To tackle the issue, we propose a novel machine learning based peptide design architecture, called Latent Space Approximate Trajectory Collector (LSATC). It consists of a series of samplers on an optimization trajectory on a highly non-convex energy landscape that approximates the distributions of peptides with desired properties in a latent space. The process involves little human intervention and can be implemented in an end-to-end manner. We demonstrate the model by the design of peptide extensions targeting Beta-catenin, a key nuclear effector protein involved in canonical Wnt signalling. When compared with a random sampler, LSATC can sample peptides with $36\%$ lower binding scores in a $16$ times smaller interquartile range (IQR) and $284\%$ less hydrophobicity with a $1.4$ times smaller IQR. LSATC also largely outperforms other common generative models. Finally, we utilized a clustering algorithm to select 4 peptides from the 100 LSATC designed peptides for experimental validation. The result confirms that all the four peptides extended by LSATC show improved Beta-catenin binding by at least $20.0\%$, and two of the peptides show a $3$ fold increase in binding affinity as compared to the base peptide.

cs.CE↗

arXiv2022

Hierarchical Automatic Power Plane Generation with Genetic Optimization and Multilayer Perceptron

We present an automatic multilayer power plane generation method to accelerate the design of printed circuit boards (PCB). In PCB design, while automatic solvers have been developed to predict important indicators such as the IR-drop, power integrity, and signal integrity, the generation of the power plane itself still largely relies on laborious manual methods. Our automatic power plane generation approach is based on genetic optimization combined with a multilayer perceptron and is able to automatically generate power planes across a diverse set of problems with varying levels of difficulty. Our method GOMLP consists of an outer loop genetic optimizer (GO) and an inner loop multi-layer perceptron (MLP) that generate power planes automatically. The critical elements of our approach include contour detection, feature expansion, and a distance measure to enable island-minimizing complex power plane generation. We compare our approach to a baseline solution based on A*. The A* method consisting of a sequential island generation and merging process which can produce less than ideal solutions. Our experimental results show that on single layer power plane problems, our method outperforms A* in 71% of the problems with varying levels of board layout difficulty. We further describe H-GOMLP, which extends GOMLP to multilayer power plane problems using hierarchical clustering and net similarities based on the Hausdorff distance.

cs.NE↗

arXiv2022

Concurrent build direction, part segmentation, and topology optimization for additive manufacturing using neural networks

We propose a neural network-based approach to topology optimization that aims to reduce the use of support structures in additive manufacturing. Our approach uses a network architecture that allows the simultaneous determination of an optimized: (1) part segmentation, (2) the topology of each part, and (3) the build direction of each part that collectively minimize the amount of support structure. Through training, the network learns a material density and segment classification in the continuous 3D space. Given a problem domain with prescribed load and displacement boundary conditions, the neural network takes as input 3D coordinates of the voxelized domain as training samples and outputs a continuous density field. Since the neural network for topology optimization learns the density distribution field, analytical solutions to the density gradient can be obtained from the input-output relationship of the neural network. We demonstrate our approach on several compliance minimization problems with volume fraction constraints, where support volume minimization is added as an additional criterion to the objective function. We show that simultaneous optimization of part segmentation along with the topology and print angle optimization further reduces the support structure, compared to a combined print angle and topology optimization without segmentation.

cs.LG↗

arXiv2020

Placement in Integrated Circuits using Cyclic Reinforcement Learning and Simulated Annealing

Physical design and production of Integrated Circuits (IC) is becoming increasingly more challenging as the sophistication in IC technology is steadily increasing. Placement has been one of the most critical steps in IC physical design. Through decades of research, partition-based, analytical-based and annealing-based placers have been enriching the placement solution toolbox. However, open challenges including long run time and lack of ability to generalize continue to restrict wider applications of existing placement tools. We devise a learning-based placement tool based on cyclic application of Reinforcement Learning (RL) and Simulated Annealing (SA) by leveraging the advancement of RL. Results show that the RL module is able to provide a better initialization for SA and thus leads to a better final placement design. Compared to other recent learning-based placers, our method is majorly different with its combination of RL and SA. It leverages the RL model's ability to quickly get a good rough solution after training and the heuristic's ability to realize greedy improvements in the solution.

cs.AI↗

arXiv2020

Real-time Prediction of Soft Tissue Deformations Using Data-driven Nonlinear Presurgical Simulations

Imaging modalities provide clinicians with real-time visualization of anatomical regions of interest (ROI) for the purpose of minimally invasive surgery. During the procedure, low-resolution image data are acquired and registered with high-resolution preoperative 3D reconstruction to guide the execution of surgical preplan. Unfortunately, due to the potential large strain and nonlinearities in the deformation of soft biological tissues, significant mismatch may be observed between ROI shapes during pre- and intra-operative imaging stages, making the surgical preplan prone to failure. In an effort to bridge the gap between the two imaging stages, this paper presents a data-driven approach based on artificial neural network for predicting the ROI deformation in real-time with sparsely registered fiducial markers. For a head-and-neck tumor model with an average maximum displacement of 30 mm, the maximum surface offsets between benchmarks and predictions using the proposed approach for 98% of the test cases are under 1.0 mm, which is the typical resolution of high-quality interventional ultrasound. Each of the prediction processes takes less than 0.5 s. With the resulting prediction accuracy and computational efficiency, the proposed approach demonstrates its potential to be clinically relevant.

physics.med-ph↗

arXiv2020

Track-Assignment Detailed Routing Using Attention-based Policy Model With Supervision

Detailed routing is one of the most critical steps in analog circuit design. Complete routing has become increasingly more challenging in advanced node analog circuits, making advances in efficient automatic routers ever more necessary. In this work, we propose a machine learning driven method for solving the track-assignment detailed routing problem for advanced node analog circuits. Our approach adopts an attention-based reinforcement learning (RL) policy model. Our main insight and advancement over this RL model is the use of supervision as a way to leverage solutions generated by a conventional genetic algorithm (GA). For this, our approach minimizes the Kullback-Leibler divergence loss between the output from the RL policy model and a solution distribution obtained from the genetic solver. The key advantage of this approach is that the router can learn a policy in an offline setting with supervision, while improving the run-time performance nearly 100x over the genetic solver. Moreover, the quality of the solutions our approach produces matches well with those generated by GA. We show that especially for complex problems, our supervised RL method provides good quality solution similar to conventional attention-based RL without comprising run time performance. The ability to learn from example designs and train the router to get similar solutions with orders of magnitude run-time improvement can impact the design flow dramatically, potentially enabling increased design exploration and routability-driven placement.

cs.LG↗

arXiv2020

StressGAN: A Generative Deep Learning Model for 2D Stress Distribution Prediction

Using deep learning to analyze mechanical stress distributions has been gaining interest with the demand for fast stress analysis methods. Deep learning approaches have achieved excellent outcomes when utilized to speed up stress computation and learn the physics without prior knowledge of underlying equations. However, most studies restrict the variation of geometry or boundary conditions, making these methods difficult to be generalized to unseen configurations. We propose a conditional generative adversarial network (cGAN) model for predicting 2D von Mises stress distributions in solid structures. The cGAN learns to generate stress distributions conditioned by geometries, load, and boundary conditions through a two-player minimax game between two neural networks with no prior knowledge. By evaluating the generative network on two stress distribution datasets under multiple metrics, we demonstrate that our model can predict more accurate high-resolution stress distributions than a baseline convolutional neural network model, given various and complex cases of geometry, load and boundary conditions.

cs.CV↗

arXiv2020

Attention Routing: track-assignment detailed routing using attention-based reinforcement learning

In the physical design of integrated circuits, global and detailed routing are critical stages involving the determination of the interconnected paths of each net on a circuit while satisfying the design constraints. Existing actual routers as well as routability predictors either have to resort to expensive approaches that lead to high computational times, or use heuristics that do not generalize well. Even though new, learning-based routing methods have been proposed to address this need, requirements on labelled data and difficulties in addressing complex design rule constraints have limited their adoption in advanced technology node physical design problems. In this work, we propose a new router: attention router, which is the first attempt to solve the track-assignment detailed routing problem using reinforcement learning. Complex design rule constraints are encoded into the routing algorithm and an attention-model-based REINFORCE algorithm is applied to solve the most critical step in routing: sequencing device pairs to be routed. The attention router and its baseline genetic router are applied to solve different commercial advanced technologies analog circuits problem sets. The attention router demonstrates generalization ability to unseen problems and is also able to achieve more than 100 times acceleration over the genetic router without significantly compromising the routing solution quality. We also discover a similarity between the attention router and the baseline genetic router in terms of positive correlations in cost and routing patterns, which demonstrate the attention router's ability to be utilized not only as a detailed router but also as a predictor for routability and congestion.

cs.LG↗

arXiv2020

TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain

In topology optimization using deep learning, load and boundary conditions represented as vectors or sparse matrices often miss the opportunity to encode a rich view of the design problem, leading to less than ideal generalization results. We propose a new data-driven topology optimization model called TopologyGAN that takes advantage of various physical fields computed on the original, unoptimized material domain, as inputs to the generator of a conditional generative adversarial network (cGAN). Compared to a baseline cGAN, TopologyGAN achieves a nearly $3\times$ reduction in the mean squared error and a $2.5\times$ reduction in the mean absolute error on test problems involving previously unseen boundary conditions. Built on several existing network models, we also introduce a hybrid network called U-SE(Squeeze-and-Excitation)-ResNet for the generator that further increases the overall accuracy. We publicly share our full implementation and trained network.

cs.CE↗

arXiv2019

Structural Design Using Laplacian Shells

We introduce a method to design lightweight shell objects that are structurally robust under the external forces they may experience during use. Given an input 3D model and a general description of the external forces, our algorithm generates a structurally-sound minimum weight shell object. Our approach works by altering the local shell thickness repeatedly based on the stresses that develop inside the object. A key issue in shell design is that large thickness values might result in self-intersections on the inner boundary creating a significant computational challenge during optimization. To address this, we propose a shape parametrization based on the solution to the Laplace's equation that guarantees smooth and intersection-free shell boundaries. Combined with our gradient-free optimization algorithm, our method provides a practical solution to the structural design of hollow objects with a single inner cavity. We demonstrate our method on a variety of problems with arbitrary 3D models under complex force configurations and validate its performance with physical experiments.

cs.CG↗

arXiv2019

A Deep Reinforcement Learning Approach for Global Routing

Global routing has been a historically challenging problem in electronic circuit design, where the challenge is to connect a large and arbitrary number of circuit components with wires without violating the design rules for the printed circuit boards or integrated circuits. Similar routing problems also exist in the design of complex hydraulic systems, pipe systems and logistic networks. Existing solutions typically consist of greedy algorithms and hard-coded heuristics. As such, existing approaches suffer from a lack of model flexibility and non-optimum solutions. As an alternative approach, this work presents a deep reinforcement learning method for solving the global routing problem in a simulated environment. At the heart of the proposed method is deep reinforcement learning that enables an agent to produce an optimal policy for routing based on the variety of problems it is presented with leveraging the conjoint optimization mechanism of deep reinforcement learning. Conjoint optimization mechanism is explained and demonstrated in details; the best network structure and the parameters of the learned model are explored. Based on the fine-tuned model, routing solutions and rewards are presented and analyzed. The results indicate that the approach can outperform the benchmark method of a sequential A* method, suggesting a promising potential for deep reinforcement learning for global routing and other routing or path planning problems in general. Another major contribution of this work is the development of a global routing problem sets generator with the ability to generate parameterized global routing problem sets with different size and constraints, enabling evaluation of different routing algorithms and the generation of training datasets for future data-driven routing approaches.

cs.LG↗

arXiv2019

Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks

The demand for fast and accurate structural analysis is becoming increasingly more prevalent with the advance of generative design and topology optimization technologies. As one step toward accelerating structural analysis, this work explores a deep learning based approach for predicting the stress fields in 2D linear elastic cantilevered structures subjected to external static loads at its free end using convolutional neural networks (CNN). Two different architectures are implemented that take as input the structure geometry, external loads, and displacement boundary conditions, and output the predicted von Mises stress field. The first is a single input channel network called SCSNet as the baseline architecture, and the second is the multi-channel input network called StressNet. Accuracy analysis shows that StressNet results in significantly lower prediction errors than SCSNet on three loss functions, with a mean relative error of 2.04% for testing. These results suggest that deep learning models may offer a promising alternative to classical methods in structural design and topology optimization. Code and dataset are available at https://github.com/zhenguonie/stress_net

cs.LG↗