Search for: All records

The present study aims to configure and train a data-driven geometry-specific surrogate model (DD GSM) to simulate the load–displacement behavior until fracture in cylindrical notched specimens subjected to uniaxial monotonic tension tests. Plastic strain hardening that governs the load–displacement behavior and ductile fracture in metals are history-dependent phenomena. With this, the load–displacement response until ductile fracture in metals is hypothesized as time sequence data. To test our hypothesis, a long short-term memory (LSTM) based deep neural network was configured and trained. LSTM is a type of neural network that takes sequential data as input and forecasts the future based on the learned past sequential trend. In this study, the trained LSTM network is referred to as DD GSM as it is used to forecast the load–displacement behavior until ductile fracture for the cylindrical notched specimens. The DD GSM is trained using the load–displacement data until fracture, extracted from the finite element analyses of notched cylindrical test specimens made of ASTM A992 steel. The damage leading to fracture was captured using the Gurson–Tvergaard–Needleman (GTN) model. Finally, the trained DD GSM is validated by predicting the overall load–displacement behavior, fracture displacement, and peak load-carrying capacity of cylindrical notched ASTM A992 structural steel specimens available in the literature that are not used for training purposes. The DD GSM was able to forecast some portions of the load–displacement curve and predict the fracture displacement and peak load-carrying capacity of the notched specimens. Furthermore, the geometric sensitivity of the trained DD GSM was demonstrated by simulating the load–displacement response of an ASTM A992 steel bar with a central hole. 

ABSTRACT A novel approach was proposed and implemented to assess the confidence of the individual class predictions made by convolutional neural networks trained to identify the type of fracture in metals. This approach involves utilizing contextual evidence in the form of contextual fracture images and contextual scores, which serve as indicators for determining the certainty of the predictions. This approach was first tested on both shallow and deep convolutional neural networks employing four publicly available image datasets: MNIST, EMNIST, FMNIST, and CIFAR10, and subsequently validated on an in‐house steel fracture dataset—FRAC, containing ductile and brittle fracture images. The effectiveness of the method is validated by producing contextual images and scores for the fracture image data and other image datasets to assess the confidence of selected predictions from the datasets. The CIFAR‐10 dataset yielded the lowest mean contextual score of 78 for the shallow model, with over 50% of representative test instances receiving a score below 90, indicating lower confidence in the model's predictions. In contrast, the CNN model used for the fracture dataset achieved a mean contextual score of 99, with 0% of representative test instances receiving a score below 90, suggesting a high level of confidence in its predictions. This approach enhances the interpretability of trained convolutional neural networks and provides greater insight into the confidence of their outputs. 

Additive manufacturing (AM) provides exceptional geometrical freedom to the architects and designers and enables the construction of architecturally exposed steel structures. However, the AM structural elements inherently possess microscale defects that can affect their ductility. This study aims to identify the fracture-initiating mechanism in AM 17-4 stainless steel that is popularly used owing to its excellent engineering properties. To this end, axisymmetric cylindrical notched and unnotched tension specimens are manufactured employing direct metal laser sintering from 17-4 stainless steel powder with established processing and build parameters. The test specimens were manufactured using a 90° build orientation with the build plate and a layer thickness of 40 μm. Postprocessing heat treatment was avoided as the study focused on understanding the failure mechanism in as-built AM test specimens. Detailed metallurgical analysis is performed employing scanning electron microscopy (SEM) and electron backscatter diffraction. Subsequently, micro–computed tomography (CT) studies are conducted on the tension specimens before and after mechanical testing. Although the SEM analyses of fracture surfaces are inconclusive, the micro-CT analysis revealed evidence of nucleation of new microvoids, growth of existing voids, and void coalescence in the vicinity of the fracture surface, which is unequivocal evidence for ductile fracture. Furthermore, the larger AM defects were found to play an important role in lowering the ductility in addition to stress concentration, and the fracture was initiated when the AM defects coalesced over a length of around 600 μm. The conclusions of this study emphasize the importance of controlling the maximum size of defects in AM structural elements to improve their performance. 

The present study aims to characterize the microvoid sizes and their statistical distribution at the instance of fracture from the fracture surface of steel specimens. To this end, uniaxial tensile tests are conducted on circumferentially notched specimens made of 17-4 PH stainless steel and ASTM A992 high-strength structural steel. The fracture surfaces of the steel test specimens are studied using a digital microscope to quantify the statistical microvoid size distribution. Furthermore, the evaluated microvoid sizes of different fracture locations are mapped with the stress and strain fields. Finally, based on the experimentally evaluated microvoid sizes, an uncoupled fracture model was adopted to predict the fracture displacement and location of ductile fracture initiation in the fractured specimens. The fracture displacements predicted using the calibrated uncoupled fracture model are within the acceptable limit. The fracture initiation locations coincided with the peak strain-averaged stress triaxiality in the fracture specimens.