Quantum and complex-valued hybrid networks for multi-principal element alloys phase prediction

Summary: This study introduces a hybrid network model for phase classification, integrating quantum networks and complex-valued neural networks. This architecture uses elemental composition as its only input, eliminating complex feature engineering. Parameterized quantum networks handle sparse eleme...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaochun Li, Yutong Sun, Lu Xiao, Weimin Long, Gang Wang, Junzhi Cui, Jingli Ren
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:iScience
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589004224028098
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850103023588605952
author Shaochun Li
Yutong Sun
Lu Xiao
Weimin Long
Gang Wang
Junzhi Cui
Jingli Ren
author_facet Shaochun Li
Yutong Sun
Lu Xiao
Weimin Long
Gang Wang
Junzhi Cui
Jingli Ren
author_sort Shaochun Li
collection DOAJ
description Summary: This study introduces a hybrid network model for phase classification, integrating quantum networks and complex-valued neural networks. This architecture uses elemental composition as its only input, eliminating complex feature engineering. Parameterized quantum networks handle sparse elemental data and convert data from real to complex domains, increasing information dimensionality. Complex-valued neural networks process data in the complex domain, significantly reducing information loss during transitions. The experimental results show that the hybrid model achieves a phase classification accuracy of 94.93%, outperforming the best machine learning model by 2.27% and the quantum model by 8.67%. Precision, recall, and F1-score are also excellent at 0.9494, 0.9493, and 0.9500, respectively. Additional tests on phase transitions in AlxCoCrFeNi alloys confirm the model’s robust generalization, identifying transition thresholds at 0.46 and 0.88, closely matching the 0.45 and 0.88 reported in related studies.
format Article
id doaj-art-6eb25fbe2a294592904cef2ebcc643f5
institution DOAJ
issn 2589-0042
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series iScience
spelling doaj-art-6eb25fbe2a294592904cef2ebcc643f52025-08-20T02:39:38ZengElsevieriScience2589-00422025-01-0128111158210.1016/j.isci.2024.111582Quantum and complex-valued hybrid networks for multi-principal element alloys phase predictionShaochun Li0Yutong Sun1Lu Xiao2Weimin Long3Gang Wang4Junzhi Cui5Jingli Ren6School of Mathematics and Statistics, Zhengzhou University, Zhengzhou 450001, ChinaInstitute of Systems Science, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Mathematics and Statistics, Zhengzhou University, Zhengzhou 450001, ChinaSKL of Advanced Brazing Metals & Technology, Zhengzhou Research Institute of Mechanical Engineering, Zhengzhou 450001, ChinaInstitute of Materials, Shanghai University, Shanghai 200444, ChinaInstitute of Computational Mathematics, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Mathematics and Statistics, Zhengzhou University, Zhengzhou 450001, China; Corresponding authorSummary: This study introduces a hybrid network model for phase classification, integrating quantum networks and complex-valued neural networks. This architecture uses elemental composition as its only input, eliminating complex feature engineering. Parameterized quantum networks handle sparse elemental data and convert data from real to complex domains, increasing information dimensionality. Complex-valued neural networks process data in the complex domain, significantly reducing information loss during transitions. The experimental results show that the hybrid model achieves a phase classification accuracy of 94.93%, outperforming the best machine learning model by 2.27% and the quantum model by 8.67%. Precision, recall, and F1-score are also excellent at 0.9494, 0.9493, and 0.9500, respectively. Additional tests on phase transitions in AlxCoCrFeNi alloys confirm the model’s robust generalization, identifying transition thresholds at 0.46 and 0.88, closely matching the 0.45 and 0.88 reported in related studies.http://www.sciencedirect.com/science/article/pii/S2589004224028098Artificial intelligenceMaterials scienceMaterials classAlloys
spellingShingle Shaochun Li
Yutong Sun
Lu Xiao
Weimin Long
Gang Wang
Junzhi Cui
Jingli Ren
Quantum and complex-valued hybrid networks for multi-principal element alloys phase prediction
iScience
Artificial intelligence
Materials science
Materials class
Alloys
title Quantum and complex-valued hybrid networks for multi-principal element alloys phase prediction
title_full Quantum and complex-valued hybrid networks for multi-principal element alloys phase prediction
title_fullStr Quantum and complex-valued hybrid networks for multi-principal element alloys phase prediction
title_full_unstemmed Quantum and complex-valued hybrid networks for multi-principal element alloys phase prediction
title_short Quantum and complex-valued hybrid networks for multi-principal element alloys phase prediction
title_sort quantum and complex valued hybrid networks for multi principal element alloys phase prediction
topic Artificial intelligence
Materials science
Materials class
Alloys
url http://www.sciencedirect.com/science/article/pii/S2589004224028098
work_keys_str_mv AT shaochunli quantumandcomplexvaluedhybridnetworksformultiprincipalelementalloysphaseprediction
AT yutongsun quantumandcomplexvaluedhybridnetworksformultiprincipalelementalloysphaseprediction
AT luxiao quantumandcomplexvaluedhybridnetworksformultiprincipalelementalloysphaseprediction
AT weiminlong quantumandcomplexvaluedhybridnetworksformultiprincipalelementalloysphaseprediction
AT gangwang quantumandcomplexvaluedhybridnetworksformultiprincipalelementalloysphaseprediction
AT junzhicui quantumandcomplexvaluedhybridnetworksformultiprincipalelementalloysphaseprediction
AT jingliren quantumandcomplexvaluedhybridnetworksformultiprincipalelementalloysphaseprediction