This research proposes a new framework to develop an accurate machine-learning-based surrogate model to predict the optimum topological structures using an advanced encoder–decoder network, Unet, and Unet++. The trained surrogate model predicts the optimum structural layout as output by inputting the results from the initial static analysis without any iterative optimization calculations. Input and output data are generated using the commercial finite element analysis package, Abaqus/Standard, and an optimization package, Abaqus/Tosca. We applied the data augmentation technique to increase the amount of data without actual calculations. Primarily, this research focused on overcoming the weaknesses of previous studies that the trained network is only applicable to limited geometry variations and requires an organized grid rectangular mesh. Therefore, this study suggests a mapping process to convert the analysis data on any type of mesh element to a tensor form, which enables training and employing the network. Also, to increase the prediction accuracy, we trained the network with the labeled optimum material data using a binary segmented output, representing the structure and void regions in the domain. Finally, the trained networks are evaluated using the intersection over union (IoU) scores representing the classification accuracy. The best-performing network provides highly accurate results, and this model provided the IoU scores for average, maximum, and standard deviation as 90.0%, 99.8%, and 7.1%, respectively. Also, we apply it to solve local-global structural optimization problems, and the overall calculation time is reduced by 98%.

This research develops a highly effective deep-learning-based surrogate model that can provide the optimum topologies of 2D and 3D structures. In general, structural topology optimization requires plenty of computations because of a large number of finite element analyses to obtain optimal structural layouts by reducing the weight and satisfying the constraints. Therefore, many researchers have developed a deep-learning-based model using the initial static analysis results to predict the optimum designs. However, these studies still considered relatively simple example problems, such as a cantilever plate and MBB beam, even though they required a large number of data to achieve an accurate surrogate model for the simple application. To overcome these limitations, we propose a new framework, which 1) efficiently uses limited data by normalizing it and 2) employs a surrogate model capable of handling more practical cases, such as a 2D panel and 3D stiffened panel subjected to a distributed load, and can be used for local–global structural optimization. In all cases, the developed surrogate models can predict the optimum layouts with structural performance levels equal to those of the structures considered to be ground truths. Also, when the optimal structures were obtained using the proposed method, the total calculation time was reduced by 98% as compared to conventional topology optimization once the convolutional neural network had been trained.

The paper describes a fully automated process to generate a shell-based finite element model of a large hybrid truck chassis to perform mass optimization considering multiple load cases and multiple constraints. A truck chassis consists of different parts that could be optimized using shape and size optimization. The cross members are represented by beams, and other components of the truck (batteries, engine, fuel tanks, etc.) are represented by appropriate point masses and are attached to the rail using multiple point constraints to create a mathematical model. Medium-fidelity finite element models are developed for front and rear suspensions and they are attached to the chassis using multiple point constraints, hence creating the finite element model of the complete truck. In the optimization problem, a set of five load conditions, each of which corresponds to a road event, is considered, and constraints are imposed on maximum allowable von Mises stress and the first vertical bending frequency. The structure is optimized by implementing the particle swarm optimization algorithm using parallel processing. A mass reduction of about 13.25% with respect to the baseline model is achieved.

This research proposes a framework for categorizing the radial tire mode shapes using machine learning (ML) based classification and feature recognition algorithms, advancing the development of a digital twin for tire performance analysis. Tire mode shape categorization is required to identify modal features in a specific frequency range to maximize driving performance and secure safety. However, the mode categorization work requires a lot of manual effort to interpret modes. Therefore, this study suggests an ML-based classification tool to replace the conventional categorization process with two primary objectives: (1) create a database by categorizing the tire mode shapes based on the identified features and (2) develop an ML-based surrogate model to classify the tire mode shapes without manual effort. The feature map of the tire mode shape is built with the Zernike annular moment descriptor (ZAMD). The mode shapes are categorized using the correlation value derived by the modal assurance criteria (MAC) with all ZAMD values for each tire mode shape and subsequently creating the appropriate labels. The decision tree, random forests, and XGBoost, the representative supervised-learning algorithms for classification, are implemented for surrogate model development. The best-performed classifier can categorize the mode shapes without any manual effort with a high accuracy of 99.5%.

This study estimates ground-level fine particulate matter (PM_2.5) concentrations using geostationary satellites-derived Aerosol Optical Depth (AOD) and radiance measurements and meteorological parameters from the High-Resolution Rapid Refresh (HRRR) model, with AirNow PM_2.5 measurements over the contiguous United States (CONUS). A Deep Neural Network (DNN) was adopted and compared with other machine learning (ML) models (i.e., Random Forest and Light Gradient-Boosting Machine) to estimate surface PM_2.5 concentrations. The DNN model (without the tropospheric emissions: monitoring of pollution (TEMPO); 1 year) estimated PM_2.5 with an interquartile range (IQR) of 4.32 μg/m³, and outperformed ML models, with up to 44.68% better index of agreement (IOA) and 45.28% smaller relative root-mean-square error (rRMSE), particularly in high PM_2.5 cases. The hourly estimated PM_2.5 closely matched the observed PM_2.5 in both temporal trend and spatial distribution across the eastern CONUS. ML modeling was further enhanced to include TEMPO Level 1b (L1b) data. The DNN model with TEMPO improved performance, with an 8% higher R ² and a 25% lower rRMSE than the DNN model without TEMPO. The more significant improvement was seen during high smoke events using the TEMPO data. For the first time, we demonstrate the use of TEMPO L1b spectrally resolved radiances data to capture high PM_2.5 concentrations during the wildfire events, enhancing our understanding of PM_2.5 dynamics. This study provides a framework to integrate data from multiple geostationary satellites with HRRR model outputs to estimate surface air quality at high temporal resolution.