文章信息/Info

Title:

Current Status and Future Prospects of Material Databases: Innovative Applications Led by AI Technology

文章編號(hào):

1674-3962(2026)02-0089-13

作者:

馮建發(fā);  王暢暢;  蘇航;  宿彥京

1. 北京科技大學(xué) 新材料技術(shù)研究院，北京 100083 2. 北京新材道數(shù)智科技有限公司, 北京 100081 3. 中國(guó)鋼研科技集團(tuán)有限公司數(shù)字化研發(fā)中心, 北京 100081

Author(s):

FENG Jianfa;  WANG Changchang;  SU Hang;  SU Yanjing

1. Institute for Advanced Materials and Technology, University of Science and Technology Beijing, Beijing 100083, China 2. Beijing MatDao Technology Co��, Ltd��, Beijing 100081, China 3. Material Digital R&D Center, China Iron & Steel Research Institute Group, Beijing 100081, China

關(guān)鍵詞:

材料數(shù)據(jù)庫(kù); 大數(shù)據(jù)技術(shù); AI; 機(jī)器學(xué)習(xí); 大模型

Keywords:

material database;  big data technology;  AI;  machine learning;  large model

分類號(hào):

TB30;TP18

DOI:

10.7502/j.issn.1674-3962.202411028

文獻(xiàn)標(biāo)志碼:

A

摘要:

隨著人工智能技術(shù)的不斷進(jìn)步，材料數(shù)據(jù)庫(kù)在材料科學(xué)研究中扮演著日益重要的角色。旨在探討材料數(shù)據(jù)庫(kù)如何通過(guò)與AI技術(shù)的融合，擴(kuò)展其應(yīng)用范圍并提升其核心價(jià)值。通過(guò)文獻(xiàn)綜述的方法，系統(tǒng)地分析了材料數(shù)據(jù)庫(kù)的當(dāng)前分類，包括材料基礎(chǔ)數(shù)據(jù)庫(kù)、生產(chǎn)加工數(shù)據(jù)庫(kù)、應(yīng)用服役數(shù)據(jù)庫(kù)等，并概述了支撐技術(shù)如機(jī)器學(xué)習(xí)、深度學(xué)習(xí)、數(shù)據(jù)標(biāo)準(zhǔn)化技術(shù)的應(yīng)用情況。盡管國(guó)際上材料數(shù)據(jù)庫(kù)的發(fā)展呈現(xiàn)出智能化、網(wǎng)絡(luò)化、資產(chǎn)化、去中心化的趨勢(shì)，但在數(shù)據(jù)質(zhì)量、數(shù)據(jù)共享、知識(shí)產(chǎn)權(quán)、市場(chǎng)運(yùn)維等方面仍面臨挑戰(zhàn)。未來(lái)材料數(shù)據(jù)庫(kù)的發(fā)展將受益于與新興技術(shù)如材料數(shù)據(jù)工廠、區(qū)塊鏈、隱私計(jì)算、AI大模型的結(jié)合，這將為新材料的研發(fā)和應(yīng)用提供創(chuàng)新的手段和場(chǎng)景工具。

Abstract:

With the continuous advancement of artificial intelligence (AI) technology, material databases are increasingly playing a pivotal role in materials science research. This paper aims to explore how the integration of AI technology can expand the application scope and enhance the core value of material databases. Through a literature review, the current classifications of material databases were systematically analyzed, including material basic databases, production and processing databases, and application service databases, and outlined the application of supporting technologies such as machine learning, deep learning, and data standardization. Despite the international development of material databases showing trends towards intelligence, networking, assetization, and decentralization, challenges remain in terms of data quality, data sharing, intellectual property rights, and market operation and maintenance. The future development of material databases is expected to benefit from the integration with emerging technologies such as material data factories, blockchain, privacy computing, and AI large models, which will provide innovative means and tools for the research and development and application of new materials.