An official website of the United States government
Abstract High‐throughput screening has become one of the major strategies for the discovery of novel functional materials. However, its effectiveness is severely limited by the lack of sufficient and diverse materials in current materials repositories such as the open quantum materials database (OQMD). Recent progress in deep learning have enabled generative strategies that learn implicit chemical rules for creating hypothetical materials with new compositions and structures. However, current materials generative models have difficulty in generating structurally diverse, chemically valid, and stable materials. Here we propose CubicGAN, a generative adversarial network (GAN) based deep neural network model for large scale generative design of novel cubic materials. When trained on 375 749 ternary materials from the OQMD database, the authors show that the model is able to not only rediscover most of the currently known cubic materials but also generate hypothetical materials of new structure prototypes. A total of 506 such materials have been verified by phonon dispersion calculation. Considering the importance of cubic materials in wide applications such as solar panels, the GAN model provides a promising approach to significantly expand existing materials repositories, enabling the discovery of new functional materials via screening. The new crystal structures discovered are freely accessible atwww.carolinamatdb.org.
more »
« less
This content will become publicly available on March 15, 2026
Generative Design of Thermoset Shape Memory Polymers Driven by Chemical Group: A Conditional Variational Autoencoder Approach
ABSTRACT The discovery of novel thermoset shape memory polymers (TSMPs) for additive manufacturing can be accelerated through the use of a deep‐generative algorithm, minimizing the need for laborious traditional laboratory experiments. This study is the first to introduce an innovative approach that uses a deep generative learning model, namely the conditional variational autoencoder (CVAE), to discover novel TSMPs with lower glass transition temperature () and high recovery stress values (). In this study, specific chemical groups, such as epoxy, amine, thiol, and vinyl, are integrated as constraints to generate novel TSMPs while preserving the essential reaction properties. To address the challenges posed by a small dataset, the CVAE model is used with graph‐extracted features. Unlike previous studies focused on single‐polymer systems, this research extends to two‐monomer samples, discovering 22 novel TSMPs. This approach has practical implications in additive manufacturing, biomedical devices, aerospace, and robotics for the discovery of novel samples from limited data.
more »
« less
- Award ID(s):
- 1946231
- PAR ID:
- 10580660
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Journal of Polymer Science
- Volume:
- 63
- Issue:
- 6
- ISSN:
- 2642-4150
- Page Range / eLocation ID:
- 1334 to 1344
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
PurposeThe purpose of this study is to develop a deep learning framework for additive manufacturing (AM), that can detect different defect types without being trained on specific defect data sets and can be applied for real-time process control. Design/methodology/approachThis study develops an explainable artificial intelligence (AI) framework, a zero-bias deep neural network (DNN) model for real-time defect detection during the AM process. In this method, the last dense layer of the DNN is replaced by two consecutive parts, a regular dense layer denoted (L1) for dimensional reduction, and a similarity matching layer (L2) for equal weight and non-biased cosine similarity matching. Grayscale images of 3D printed samples acquired during printing were used as the input to the zero-bias DNN. FindingsThis study demonstrates that the approach is capable of successfully detecting multiple types of defects such as cracks, stringing and warping with high accuracy without any prior training on defective data sets, with an accuracy of 99.5%. Practical implicationsOnce the model is set up, the computational time for anomaly detection is lower than the speed of image acquisition indicating the potential for real-time process control. It can also be used to minimize manual processing in AI-enabled AM. Originality/valueTo the best of the authors’ knowledge, this is the first study to use zero-bias DNN, an explainable AI approach for defect detection in AM.more » « less
-
Generative Moment-Matching Network (GMMN) is a deep generative model, which employs maximum mean discrepancy as the objective to learn model parameters. However, this model can only generate samples, failing to infer the latent code from samples for downstream tasks. In this paper, we propose a novel Joint Generative Moment-Matching Network (JGMMN), which learns the structural latent code for unsupervised inference. Specifically, JGMMN has a generation network for the generation task and an inference network for the inference task. We first reformulate this model as the two joint distributions matching problem. To solve this problem, we propose to use the Joint Maximum Mean Discrepancy (JMMD) as the objective to learn these two networks simultaneously. Furthermore, to enforce the consistency between the sample distribution and the inferred latent code distribution, we propose a novel multi-modal regularization to enforce this consistency. At last, extensive experiments on both synthetic and real-world datasets have verified the effectiveness and correctness of our proposed JGMMN.more » « less
-
null (Ed.)Abstract Cooperative 3D printing (C3DP) is a novel approach to additive manufacturing, where multiple printhead-carrying mobile robots work cooperatively to print the desired part. The core of C3DP is the chunk-based printing strategy in which the desired part is first split into smaller chunks and then the chunks are assigned to individual robots to print and bond. These robots will work simultaneously in a scheduled sequence to print the entire part. Although promising, C3DP lacks a generative approach that enables automatic chunking and scheduling. In this study, we aim to develop a generative approach that can automatically generate different print schedules for a chunked object by exploring a larger solution space that is often beyond the capability of human cognition. The generative approach contains (1) a random generator of diverse print schedules based on an adjacency matrix that represents a directed dependency tree structure of chunks; (2) a set of geometric constraints against which the randomly generated schedules will be checked for validation, and (3) a printing time evaluator for comparing the performance of all valid schedules. We demonstrate the efficacy of the generative approach using two case studies: a large simple rectangular bar and a miniature folding sport utility vehicle (SUV) with more complicated geometry. This study demonstrates that the generative approach can generate a large number of different print schedules for collision-free C3DP, which cannot be explored solely using human heuristics. This generative approach lays the foundation for building the optimization approach of C3DP scheduling.more » « less
-
Discovering novel molecules with targeted properties remains a formidable challenge in materials science, often likened to finding a needle in a haystack. Traditional experimental approaches are slow, costly, and inefficient. In this study, we present an inverse design framework based on a molecular graph conditional variational autoencoder (CVAE) that enables the generation of new molecules with user-specified optical properties, particularly molar extinction coefficient ($$\varepsilon$$). Our model encodes molecular graphs, derived from SMILES strings, into a structured latent space, and then decodes them into valid molecular structures conditioned on a target $$\varepsilon$$ value. Trained on a curated dataset of known molecules with corresponding extinction coefficients, the CVAE learns to generate chemically valid structures, as verified by RDKit. Subsequent Density Functional Theory (DFT) simulations confirm that many of the generated molecules exhibit the electronic structures similar to those molecules with desired $$\varepsilon$$ values. We have also verified the $$\varepsilon$$ values of the generated molecules using a graph neural network (GNN) and the synthesizability of those molecules using an open-source module named ASKCOS. This approach demonstrates the potential of CVAEs to accelerate molecular discovery by enabling user-guided, property-driven molecule generation -- offering a scalable, data-driven alternative to traditional trial-and-error synthesis.more » « less
