材料對沖擊載荷的響應(yīng)對行星科學(xué)、航空航天工程和高能材料非常重要。熱激發(fā)過程如化學(xué)反應(yīng)和相變在能量集中處會發(fā)生顯著的加速。這是由沖擊波與材料微觀結(jié)構(gòu)相互作用產(chǎn)生的結(jié)果,并受復(fù)雜的耦合過程控制,而其中的過程控制機制尚未被完全了解。
這些過程大多發(fā)生在溫度、壓力和應(yīng)變速率的極端條件下,而且其中各種能量局部集中和微觀結(jié)構(gòu)特征存在于不同長度和時間尺度。因此,現(xiàn)有的模型都無法在沒有強近似假設(shè)的情況下預(yù)測沖擊誘導(dǎo)的熱點形成。
Fig. 2 Ability of MISTnet to predict temperature fields for an unseen microstructure.
分子動力學(xué)(MD)已被廣泛用于研究激波誘導(dǎo)的熱點形成,包括孔隙率的坍塌、剪切、摩擦和局部塑性變形,但是MD方法需要巨大的計算成本。同時,深度學(xué)習(xí)已經(jīng)被用于模擬材料在沖擊載荷下的中尺度熱機械響應(yīng),其精度與基于物理的模擬相當(dāng),但只需要的計算成本相對而言非常小。
來自普渡大學(xué)材料工程學(xué)院的Alejandro Strachan教授等人,基于UNet網(wǎng)絡(luò)結(jié)構(gòu)設(shè)計了沖擊誘導(dǎo)溫度網(wǎng)絡(luò)(MISTnet),實現(xiàn)了材料中沖擊溫度場的預(yù)測。
Fig. 4 Comparison of hotspots obtained from MD and MISTnet.
作者通過MD方法對數(shù)個百萬原子規(guī)模的系統(tǒng)進行沖擊模擬采集數(shù)據(jù),通過將系統(tǒng)內(nèi)原子坐標和原子速度以及網(wǎng)格化的局部密度場作為輸入,將網(wǎng)格化的局部溫度場作為輸出,訓(xùn)練的神經(jīng)網(wǎng)絡(luò)能夠?qū)⒊跏嫉?、沖擊前的微觀結(jié)構(gòu)映射到?jīng)_擊后的溫度場,其計算成本比MD模擬的計算成本小108倍,且準確性超過了現(xiàn)有的模型。在泛化測試中,模型仍然準確地預(yù)測了熱點的形狀,雖然溫度被高估了,但卻準確地捕捉到了孔隙大小和方向的趨勢。
該工作可以減少現(xiàn)有方法的經(jīng)驗主義,并為將微觀結(jié)構(gòu)與沖擊載荷下材料的響應(yīng)聯(lián)系起來提供了有效的手段。該文近期發(fā)布于npj Computational Materials 9: 178 (2023)。
Editorial Summary
Material response to shock loading is important to planetary science, aerospace engineering, and energetic materials. Thermal excitation processes such as chemical reactions and phase transitions are significantly accelerated at energy localization. This results from the interaction of shock waves with the material’s microstructure and is controlled by complex coupling processes. The process control mechanisms are not fully understood. Most of these processes occur under extreme conditions of temperature, pressure, and strain rate, and various local energy concentrations and microstructural features exist at different length and time scales. Therefore none of the existing models are able to predict shock-induced hotspot formation without strong approximation assumptions.
Molecular dynamics (MD) has now been widely used to study shock-induced hotspot formation, including collapse of porosity, shear, friction, and local plastic deformation, but MD methods require huge computational costs. Deep learning has been used to simulate the mesoscale thermomechanical response of materials under shock loading with an accuracy comparable to physics-based simulations, but at a relatively small computational cost.?
Prof. Alejandro Strachan et al. from the School of Materials Engineering, Purdue University, designed the Microstructure-Informed Shock-induced Temperature net (MISTnet) based on the UNet network structure, in order to predict the temperature field caused by shock loading. The authors used the MD method to perform shock loading simulations on several million-atom-scale systems to collect data. They used the atomic coordinates and atomic velocities in the system as well as the gridded local density field as input, and used the gridded local temperature field as the output. The trained neural network is able to map the initial, pre-shock microstructure to the post-shock temperature field with a computational cost that is 108 times smaller than that of MD simulations and an accuracy that exceeds existing models. In generalization tests, the model still accurately predicted the shape of hot spots, and although temperatures were overestimated, it accurately captured trends in pore size and orientation. This study can reduce the empiricism of existing methods and provides an effective means to relate microstructure to material response under shock loading.?This article was recently published in npj Computational Materials 9: 178 (2023).
原文Abstract及其翻譯
Mapping microstructure to shock-induced temperature fields using deep learning (利用深度學(xué)習(xí)技術(shù)將微結(jié)構(gòu)映射到?jīng)_擊誘導(dǎo)的溫度場)
Chunyu Li, Juan Carlos Verduzco, Brian H. Lee, Robert J. Appleton & Alejandro Strachan
Abstract?The response of materials to shock loading is important to planetary science, aerospace engineering, and energetic materials. Thermally activated processes, including chemical reactions and phase transitions, are significantly accelerated by energy localization into hotspots. These result from the interaction of the shockwave with the materials’ microstructure and are governed by complex, coupled processes, including the collapse of porosity, interfacial friction, and localized plastic deformation. These mechanisms are not fully understood and the lack of models limits our ability to predict shock to detonation transition from chemistry and microstructure alone. We demonstrate that deep learning can be used to predict the resulting shock-induced temperature fields in composite materials obtained from large-scale molecular dynamics simulations with the initial microstructure as the only input. The accuracy of the Microstructure-Informed Shock-induced Temperature net (MISTnet) model is higher than the current state of the art and its evaluation requires a fraction of the computation cost.
摘要 材料對沖擊載荷的響應(yīng)對行星科學(xué)、航空航天工程和高能材料非常重要。熱激活過程,包括化學(xué)反應(yīng)和相變,會由于能量定位到熱點而顯著加速。這些是由沖擊波與材料微觀結(jié)構(gòu)相互作用產(chǎn)生的結(jié)果,并受復(fù)雜的耦合過程控制,包括孔隙的坍塌、界面摩擦和局部塑性變形等。這些機制還沒有被完全理解,且模型的缺乏限制了我們單獨從化學(xué)和微觀結(jié)構(gòu)預(yù)測沖擊帶來的轉(zhuǎn)變的能力。我們證明了深度學(xué)習(xí)可以用于預(yù)測復(fù)合材料的沖擊誘導(dǎo)溫度場,這些材料可以通過大規(guī)模分子動力學(xué)模擬得到,僅需要初始微觀結(jié)構(gòu)作為輸入。微結(jié)構(gòu)信息沖擊誘導(dǎo)溫度網(wǎng)(MISTnet)模型的精度高于目前的技術(shù)水平,其預(yù)測需要傳統(tǒng)方法計算成本的一小部分。
原創(chuàng)文章,作者:計算搬磚工程師,如若轉(zhuǎn)載,請注明來源華算科技,注明出處:http://m.xiubac.cn/index.php/2024/01/21/c458c6159e/