AI-assisted Advanced Propellant Development for Electric Propulsion

2025-09-30

AI Summary

Motivated by the urgent need for novel green propellants in electric propulsion systems, this work pioneers the application of artificial intelligence to predict propellant ionization behavior. To overcome the high computational and experimental costs associated with traditional quantum-chemical calculations and empirical measurements, we propose a cheminformatics-driven AI modeling framework based on chemical fingerprint encoding. Using the NIST WebBook dataset, we develop regression models to predict ionization energy (IE) and minimum appearance energy (E_min), and further construct a spectral similarity prediction framework to identify characteristic fragmentation patterns. Experimental results demonstrate mean relative errors of 6.87% for IE and 7.99% for E_min; in mass spectrum prediction, 78% of test samples yield predicted spectra matching the ground-truth spectra within the top-10 most similar candidates. This study establishes an efficient, scalable, data-driven paradigm for high-throughput screening of candidate electric propulsion propellants.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Artificial Intelligence algorithms are introduced in this work as a tool to predict the performance of new chemical compounds as alternative propellants for electric propulsion, focusing on predicting their ionisation characteristics and fragmentation patterns. The chemical properties and structure of the compounds are encoded using a chemical fingerprint, and the training datasets are extracted from the NIST WebBook. The AI-predicted ionisation energy and minimum appearance energy have a mean relative error of 6.87% and 7.99%, respectively, and a predicted ion mass with a 23.89% relative error. In the cases of full mass spectra due to electron ionisation, the predictions have a cosine similarity of 0.6395 and align with the top 10 most similar mass spectra in 78% of instances within a 30 Da range.

Problem

• AI predicts ionization energy of new electric propulsion propellants
• AI models fragmentation patterns for alternative chemical propellants
• AI forecasts mass spectra similarity for electron ionization compounds

Innovation

• AI predicts ionization energy of propellants
• Chemical fingerprints encode compound properties
• AI models achieve low error in mass spectra