Generative Deep Learning Framework for Inverse Design of Fuels

2025-04-16

AI Summary

Conventional fuel screening methods suffer from low efficiency and inability to rationally design high-research-octane-number (RON) fuels. Method: This study proposes a collaborative optimization variational autoencoder (Co-VAE) framework that jointly models molecular generation and property prediction end-to-end. We innovatively integrate a latent-space-guided differential evolution search strategy, incorporating the GDB-13 database, experimental RON data, and quantitative structure–property relationship (QSPR) models, enhanced by hyperparameter-balanced optimization and independent regression calibration to improve generalizability. Contribution/Results: The method significantly improves molecular reconstruction accuracy (+12.7%), chemical validity (>98%), and RON prediction performance (R² = 0.91). Within a thousand-molecule search space, it efficiently generates over one hundred novel candidate fuels with RON > 100, overcoming limitations of empirical trial-and-error and high-throughput screening.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

In the present work, a generative deep learning framework combining a Co-optimized Variational Autoencoder (Co-VAE) architecture with quantitative structure-property relationship (QSPR) techniques is developed to enable accelerated inverse design of fuels. The Co-VAE integrates a property prediction component coupled with the VAE latent space, enhancing molecular reconstruction and accurate estimation of Research Octane Number (RON) (chosen as the fuel property of interest). A subset of the GDB-13 database, enriched with a curated RON database, is used for model training. Hyperparameter tuning is further utilized to optimize the balance among reconstruction fidelity, chemical validity, and RON prediction. An independent regression model is then used to refine RON prediction, while a differential evolution algorithm is employed to efficiently navigate the VAE latent space and identify promising fuel molecule candidates with high RON. This methodology addresses the limitations of traditional fuel screening approaches by capturing complex structure-property relationships within a comprehensive latent representation. The generative model provides a flexible tool for systematically exploring vast chemical spaces, paving the way for discovering fuels with superior anti-knock properties. The demonstrated approach can be readily extended to incorporate additional fuel properties and synthesizability criteria to enhance applicability and reliability for de novo design of new fuels.

Problem

• Develops a deep learning framework for inverse fuel design
• Predicts Research Octane Number (RON) accurately
• Overcomes limitations of traditional fuel screening methods

Innovation

• Co-VAE integrates QSPR for fuel design
• Differential evolution optimizes latent space
• Hyperparameter tuning balances key metrics