文章信息/Info

Title:

Applications of Machine Learning in Lightweight Alloy Research

作者:

張思雨；李日

河北工業(yè)大學(xué)材料科學(xué)與工程學(xué)院，天津300401

Author(s):

Siyu Zhang1；Ri Li

School of Materials Science and Engineering, Hebei University of Technology, Tianjin 300130, China

關(guān)鍵詞:

機(jī)器學(xué)習(xí); 輕質(zhì)合金; 性能預(yù)測; 合金設(shè)計; 工藝優(yōu)化

Keywords:

Machine Learning;  Lightweight Alloys;  Performance Prediction;  Alloy Design;  Process Optimization

文獻(xiàn)標(biāo)志碼:

A

摘要:

輕質(zhì)合金以其低密度和高強(qiáng)度特性在航空航天、汽車、電子和建筑等領(lǐng)域具有重要應(yīng)用。然而，傳統(tǒng)的基于經(jīng)驗的“試錯法”和基于理論的模擬計算方法，需要進(jìn)行大量實驗周期長、成本高，難以滿足現(xiàn)代輕質(zhì)合金的發(fā)展需求。隨著人工智能和數(shù)據(jù)驅(qū)動技術(shù)的迅猛發(fā)展，機(jī)器學(xué)習(xí)作為目前人工智能領(lǐng)域應(yīng)用最廣泛、發(fā)展最快的分支，已廣泛應(yīng)用于材料科學(xué)，顯著加速了新材料的發(fā)現(xiàn)和優(yōu)化。本文對機(jī)器學(xué)習(xí)計算在輕質(zhì)合金研究中的應(yīng)用進(jìn)展進(jìn)行了綜述，介紹了機(jī)器學(xué)習(xí)在材料研究中的工作流程，闡述了機(jī)器學(xué)習(xí)在輕質(zhì)合金性能預(yù)測、合金設(shè)計以及工藝優(yōu)化方面的研究進(jìn)展及應(yīng)用實例。最后，對當(dāng)前機(jī)器學(xué)習(xí)在輕質(zhì)合金領(lǐng)域的研究中面臨的挑戰(zhàn)進(jìn)行了總結(jié)并對其發(fā)展前景進(jìn)行了展望。

Abstract:

Lightweight alloys, with their low density and high strength characteristics, hold significant applications in aerospace, automotive, electronics, and construction fields. However, traditional experience-based "trial and error" methods and theoretical simulation methods require a large number of experiments, which are time-consuming and costly, making it difficult to meet the demands of modern lightweight alloy development. With the rapid development of artificial intelligence and data-driven technologies, machine learning, as the most widely used and fastest-growing branch of artificial intelligence, has been extensively applied in materials science, significantly accelerating the discovery and optimization of new materials. This paper reviews the progress of machine learning calculations in the research of lightweight alloys, introduces the workflow of machine learning in materials research, and elucidates the research progress and application examples of machine learning in predicting the properties of lightweight alloys, alloy design, and process optimization. Finally, the challenges faced by current machine learning research in the field of lightweight alloys are summarized, and the development prospects are discussed.