Skip to content
DraconiticResearch
Search Sources API
197,761 studies31 sourcesUpdated 33 min ago
Peer-reviewedCC BY 4.0Polymers

An Efficient Descriptor for Tubular LDPE Melt Strength via Physics-Guided Learning and Diffusion-Based Inverse Design

  • Yifei Wang1
  • Guogang Liu1
  • Lin Liu1
  • Yue Yu1
  • Peiqian Yu1
  • Linge Ma1
  • Linlin Wei1
  • Zhe Zhou1
  • Linfeng Chen1
  • Delin Yuan1
  • Rongjuan Cong1
  1. 1National Institute of Clean-and-Low-Carbon Energy, Beijing 102209, China
Open at sourceDOICite

Abstract

Melt strength (MS) is a key parameter governing the processability and application of low-density polyethylene (LDPE), dictated by a complex interplay of molecular weight distribution (MWD), long-chain branching (LCB), and high-molecular-weight content—features poorly captured by conventional metrics like weight average molecular weight (Mw). This paper addresses the challenge by developing a physics-guided machine learning framework that constructs a list of molecular descriptors directly from full-spectrum MWD data using modern multi-detector high-temperature gel permeation chromatography (MD-GPC), explicitly aligned with the polymer entanglement fundamentals underlying melt strength. The descriptor enables accurate prediction and interpretable disentanglement of topological contributions. The paper further introduced a diffusion-based generative model for inverse design: given a target melt strength, the model proposed candidate molecular architectures and validated them through internal consistency with the learned structure–property relationships, offering a rational and data-driven strategy for the precise engineering of LDPE molecular structures, thus providing considerable flexibility for downstream engineering decisions. Practitioners may further refine or screen these candidates in light of real-world factors—including polymerization processing constraints, cost considerations for resin selection and blending, and manufacturing operation windows—thereby tailoring LDPE molecular structures/products to specific application requirements with high precision.

Related

  1. RACE: A Modular and Interpretable Radial–Angular Correlation Descriptor for Atomistic Machine Learning
    Raphael M. Tromer, Jhionathan de Lima, Cristiano Francisco Woellner +3
    Journal of Chemical Theory and ComputationPeer-reviewedCC BY 4.0Full textMaterials & polymersPMC
  2. Descriptor-guided thermodynamic screening of H2 adsorption on single-atom-doped anatase TiO2 nanoparticles with interpretable machine learning
    Mustafa Kurban, Can Polat, Erchin Serpedin +1
    Scientific ReportsPeer-reviewedCC BYFull text7 citedMaterials & polymersOpenAlex
  3. High-strength, electrochemically efficient RuO2-MXene/CNTs hybrid fibres via nanostructure design for flexible electronics and energy storage
    Mengmeng Dong, Hongjun Ke, Fuli Wang +4
    Materials & DesignPeer-reviewedCC BY-NC-ND40 citedMaterials & polymersOpenAlex
  4. Efficient dissociation of ultra-high-strength bamboo original fibers via deep eutectic solvent pretreatment for sustainable composite reinforcement.
    Ziliang Dai, Lili Zhang, Juan Yu +8
    Nature communicationsPeer-reviewedCC BY-NC-NDFull textMaterials & polymersEurope PMC
  5. Stereochemical Control of Static Strength and Dynamic Fracture for Efficient Atomization of Supramolecular Gel Propellants
    Yutao Xia, Fushuai Wang, Xue Jin +5
    ChemRxivPreprintCC BYFull textMaterials & polymersChemRxiv

Cite

BibTeXRIS
BibTeX
@article{wang2026efficient,
  title = {{An Efficient Descriptor for Tubular LDPE Melt Strength via Physics-Guided Learning and Diffusion-Based Inverse Design}},
  author = {Yifei Wang and Guogang Liu and Lin Liu and Yue Yu and Peiqian Yu and Linge Ma and Linlin Wei and Zhe Zhou and Linfeng Chen and Delin Yuan and Rongjuan Cong},
  journal = {Polymers},
  year = {2026},
  month = oct,
  doi = {10.3390/polym18192421},
  url = {https://www.mdpi.com/2073-4360/18/19/2421},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - An Efficient Descriptor for Tubular LDPE Melt Strength via Physics-Guided Learning and Diffusion-Based Inverse Design
AU  - Yifei Wang
AU  - Guogang Liu
AU  - Lin Liu
AU  - Yue Yu
AU  - Peiqian Yu
AU  - Linge Ma
AU  - Linlin Wei
AU  - Zhe Zhou
AU  - Linfeng Chen
AU  - Delin Yuan
AU  - Rongjuan Cong
PY  - 2026
DA  - 2026/10/04
JO  - Polymers
DO  - 10.3390/polym18192421
UR  - https://www.mdpi.com/2073-4360/18/19/2421
AB  - Melt strength (MS) is a key parameter governing the processability and application of low-density polyethylene (LDPE), dictated by a complex interplay of molecular weight distribution (MWD), long-chain branching (LCB), and high-molecular-weight content—features poorly captured by conventional metrics like weight average molecular weight (Mw). This paper addresses the challenge by developing a physics-guided machine learning framework that constructs a list of molecular descriptors directly from full-spectrum MWD data using modern multi-detector high-temperature gel permeation chromatography (MD-GPC), explicitly aligned with the polymer entanglement fundamentals underlying melt strength. The descriptor enables accurate prediction and interpretable disentanglement of topological contributions. The paper further introduced a diffusion-based generative model for inverse design: given a target melt strength, the model proposed candidate molecular architectures and validated them through internal consistency with the learned structure–property relationships, offering a rational and data-driven strategy for the precise engineering of LDPE molecular structures, thus providing considerable flexibility for downstream engineering decisions. Practitioners may further refine or screen these candidates in light of real-world factors—including polymerization processing constraints, cost considerations for resin selection and blending, and manufacturing operation windows—thereby tailoring LDPE molecular structures/products to specific application requirements with high precision.
SN  - 2073-4360
ER  -