skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Machine Learning‐Driven Discovery of Thermoset Shape Memory Polymers With High Glass Transition Temperature Using Variational Autoencoders
ABSTRACT The discovery of high‐performance shape memory polymers (SMPs) with enhanced glass transition temperatures (Tg) is of paramount importance in fields such as geothermal energy, oil and gas, aerospace, and other high‐temperature applications, where materials are required to exhibit shape memory effect at extremely high‐temperature conditions. Here, we employ a novel machine learning framework that integrates transfer learning with variational autoencoders (VAE) to efficiently explore the chemical design space of SMPs and identify new candidates with high Tg values. We systematically investigate the effect of different latent space dimensions on the VAE model performance. Several machine learning models are then trained to predict Tg. We find that the SVM model demonstrates the highest predictive accuracy, withR2values exceeding 0.87 and a mean absolute percentage error as low as 6.43% on the test set. Through systematic molar ratio adjustments and VAE‐based fingerprinting, we discover novel SMP candidates with Tg values between 190°C and 200°C, suitable for high‐temperature applications. These findings underscore the effectiveness of combining VAEs and SVM for SMP discovery, offering a scalable and efficient method for identifying polymers with tailored thermal properties.  more » « less
Award ID(s):
2418415
PAR ID:
10562061
Author(s) / Creator(s):
 ;  
Publisher / Repository:
Wiley Blackwell (John Wiley & Sons)
Date Published:
Journal Name:
Journal of Polymer Science
Volume:
63
Issue:
5
ISSN:
2642-4150
Format(s):
Medium: X Size: p. 1095-1107
Size(s):
p. 1095-1107
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Shape memory polymer (SMP) systems exhibiting semicrystalline- elastomer blends, such as thermoplastic polyurethane and polylactic acid have been well studied, but their use in biomedical shape memory applications has been limited by their high activation temperature. SMPs are capable of deformation and recovery through the activation of an external stimuli, such as temperature. Critical criteria for SMPs used in biomedical applications is achieving a stimulus temperature close to 37 °C while still experiencing sufficient shape recovery. A polymer’s glass transition temperature has been well defined as the SMP system’s activation temperature and therefore should be decreased to achieve a decreased activation temperature. In this work, a well-known, biocompatible plasticizer, polyethylene oxide (PEO), was added to thermoplastic polyurethane (TPU)—polylactic acid (PLA) SMP blends to observe the plasticizing effect on the structural, thermal, mechanical, and shape memory properties of the polymer blends. Additionally, the geometry of the fabricated SMP samples was tailored to further enhance the shape memory effect through a bowtie honeycomb structure. Our results suggest that the addition of PEO into the SMP system may be an effective method for decreasing the polymer’s glass transition temperature through the alteration of the polymer chain structure. With the addition of 30% PEO, the glass transition temperature of the TPU/PLA blend was successfully decreased from 62.4 °C to 34.6 °C while achieving 86.5% shape recovery when activated at 37 °C, which is only a 5% decrease in shape recovery when activated at 50 °C. These results suggest that the addition of a biocompatible plasticizer may overcome the limitation of employing temperature activated SMP systems in biomedical applications, and enhances the potential of these materials for reconfigurable structures, energy dissipation systems, and structural health monitoring (SHM) in civil engineering applications. 
    more » « less
  2. Abstract High-intensity focused ultrasound (HIFU) has been investigated as a remote and controlled activation method to noninvasively actuate shape memory polymers (SMPs), specifically in biomedical applications. However, the effects of aqueous environment on shape recoverability ofin vivoHIFU-actuated SMPs have yet to be explored. HIFU directs sound waves into a millimeter-sized tightly focused region. In this study, the response of hydrophilic and hydrophobic photopolymerized thermoset SMP networks under HIFU activation in an aqueous environment was investigated. Acrylate-based SMP networks were copolymerized in specific ratios to produce networks with independently adjusted glass transition temperatures ranging from 40 to 80 °C and two distinct water uptake behaviors. The results link the polymer swelling behavior to shape recoverability in various acoustic fields. The presence of absorbed water molecules enhances the performance of SMPs in terms of their shape memory capabilities when activated by HIFU. Overall, understanding the interplay between water uptake and HIFU-actuated shape recovery is essential for optimizing the performance of SMPs in aqueous environments and advancing their use in various medical applications. 
    more » « less
  3. Shape memory polymer (SMP) systems exhibiting semicrystalline- elastomer blends, such as thermoplastic polyurethane and polylactic acid have been well studied, but their use in biomedical shape memory applications has been limited by their high activation temperature. SMPs are capable of deformation and recovery through the activation of an external stimuli, such as temperature. Critical criteria for SMPs used in biomedical applications is achieving a stimulus temperature close to 37 °C while still experiencing sufficient shape recovery. A polymer’s glass transition temperature has been well defined as the SMP system’s activation temperature and therefore should be decreased to achieve a decreased activation temperature. In this work, a well-known, biocompatible plasticizer, polyethylene oxide (PEO), was added to thermoplastic polyurethane (TPU)—polylactic acid (PLA) SMP blends to observe the plasticizing effect on the structural, thermal, mechanical, and shape memory properties of the polymer blends. Additionally, the geometry of the fabricated SMP samples was tailored to further enhance the shape memory effect through a bowtie honeycomb structure. Our results suggest that the addition of PEO into theSMPsystem may be an effective method for decreasing the polymer’s glass transition temperature through the alteration of the polymer chain structure. With the addition of 30% PEO, the glass transition temperature of the TPU/PLA blend was successfully decreased from 62.4 °Cto 34.6 °Cwhile achieving 86.5% shape recovery when activated at 37 °C, which is only a5%decrease in shape recovery when activated at 50 °C. These results suggest that the addition of a biocompatible plasticizer may overcome the limitation of employing temperature activated SMP systems in biomedical applications, and enhances the potential of these materials for reconfigurable structures, energy dissipation systems, and structural health monitoring (SHM) in civil engineering applications. 
    more » « less
  4. Fibrous shape memory polymers (SMPs) have received growing interest in various applications, especially in biomedical applications, which offer new structures at the microscopic level and the potential of enhanced shape deformation of SMPs. In this paper, we report on the development and investigation of the properties of acrylate-based shape memory polymer fibers, fabricated by electrospinning technology with the addition of polystyrene (PS). Fibers with different diameters are manufactured using four different PS solution concentrations (25, 30, 35, and 40 wt%) and three flow rates (1.0, 2.5, and 5.0 μL min −1 ) with a 25 kV applied voltage and 17 cm electrospinning distance. Scanning electron microscope (SEM) images reveal that the average fiber diameter varies with polymer concentration and flow rates, ranging from 0.655 ± 0.376 to 4.975 ± 1.634 μm. Dynamic mechanical analysis (DMA) and stress–strain testing present that the glass transition temperature and tensile values are affected by fiber diameter distribution. The cyclic bending test directly proves that the electrospun SMP fiber webs are able to fully recover; additionally, the recovery speed is also affected by fiber diameter. With the combination of the SMP material and electrospinning technology, this work paves the way in designing and optimizing future SMP fibers properties by adjusting the fiber diameter. 
    more » « less
  5. null (Ed.)
    We present a novel optimization framework for optimal design of structures exhibiting memory characteristics by incorporating shape memory polymers (SMPs). SMPs are a class of memory materials capable of undergoing and recovering applied deformations. A finite-element analysis incorporating the additive decomposition of small strain is implemented to analyze and predict temperature-dependent memory characteristics of SMPs. The finite element method consists of a viscoelastic material modelling combined with a temperature-dependent strain storage mechanism, giving SMPs their characteristic property. The thermo-mechanical characteristics of SMPs are exploited to actuate structural deflection to enable morphing toward a target shape. A time-dependent adjoint sensitivity formulation implemented through a recursive algorithm is used to calculate the gradients required for the topology optimization algorithm. Multimaterial topology optimization combined with the thermo-mechanical programming cycle is used to optimally distribute the active and passive SMP materials within the design domain. This allows us to tailor the response of the structures to design them with specific target displacements, by exploiting the difference in the glass-transition temperatures of the two SMP materials. Forward analysis and sensitivity calculations are combined in a PETSc-based optimization framework to enable efficient multi-functional, multimaterial structural design with controlled deformations. 
    more » « less