人机协作设计基于SnTe的热电材料,通过利用大型语言模型的多代理框架
Haojian Su1, Shuai Lei2, Yazhou Chen1
1Institute of System Engineering, Academy of Military Science, Beijing 100141, China.
ACS applied materials & interfaces
|November 10, 2025
概括
本研究介绍了一个大型语言模型 (LLM) 框架,用于设计先进的热电材料. 通过LLM指导,材料性能得到了显著提高,热电功率 (zT) 增加了40%.
科学领域:
- 材料科学 材料科学 材料科学
- 人工智能的人工智能
- 能源科学 能源科学
背景情况:
- 传统的热电材料设计在很大程度上依赖于实证方法和计算模拟.
- 开发用于能源应用的高性能热电材料是一项挑战.
- 现有的方法往往缺乏从广的科学文献中提取知识的效率.
研究的目的:
- 开发一个创新的框架,用于基于SnTe的热电材料的人机协作设计.
- 利用大型语言模型 (LLM) 进行高效的知识提取和优化策略.
- 为了证明LLM指导设计在提高热电材料性能方面的有效性.
主要方法:
- 实施由LLMs驱动的多代理合作框架.
- 整合战略规划和推理模块,从文献和实验数据中提取知识.
- 基于SnTe的材料的指导实验合成和表征,其中包含Sb,Ge和Cu.
主要成果:
- 该LLM框架成功推断了优化策略和组成范围.
- 加入Sb,Ge和Cu元素调节了载体度并诱导了多尺度缺陷.
- 一个新型样本获得了约1.2的热电功率 (zT),比Sb-doped SnTe.提高了40%.
结论:
- 由LLM驱动的协作设计为材料发现提供了一个新的范式,超越了传统的方法.
- 开发的框架显著提高了热电材料的性能.
- 这种方法对能源领域的高性能材料设计具有广泛的影响,包括废热回收和固态冷却.
相关概念视频
Thermodynamic Systems
7.5K
A thermodynamic system is a set of objects whose thermodynamic properties are of interest. The system is considered to be embedded in its surroundings or the environment. The system and its environment can exchange heat and do work on each other through a boundary that separates them. However, the immediate surroundings of the system interact with it directly and therefore have a much stronger influence on its behavior and properties.
Consider an example of tea boiling in a kettle. The...
Consider an example of tea boiling in a kettle. The...
7.5K
Ampere-Maxwell's Law: Problem-Solving
1.1K
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...
1.1K
Mechanisms of Heat Transfer II
4.2K
In convection, thermal energy is carried by the large-scale flow of matter. Ocean currents and large-scale atmospheric circulation, which result from the buoyancy of warm air and water, transfer hot air from the tropics toward the poles and cold air from the poles toward the tropics. The Earth’s rotation interacts with those flows, causing the observed eastward flow of air in the temperate zones. Convection dominates heat transfer by air, and the amount of available space for the airflow...
4.2K
Mechanisms of Heat Transfer
1.6K
Heat transfer between the human body and its environment occurs through four main mechanisms: conduction, convection, radiation, and evaporation.
Conduction, accounting for approximately 3% of body heat loss at rest, is the process of exchanging heat between molecules of two materials in direct contact. This can result in both heat loss and gain. For instance, when the body is submerged in water, which conducts heat 20 times more effectively than air, it can either lose or gain significant...
Conduction, accounting for approximately 3% of body heat loss at rest, is the process of exchanging heat between molecules of two materials in direct contact. This can result in both heat loss and gain. For instance, when the body is submerged in water, which conducts heat 20 times more effectively than air, it can either lose or gain significant...
1.6K
Mechanism of heat transfer
1.8K
Understanding heat transfer mechanisms is essential for understanding how our bodies maintain balance in different environmental conditions. When the environment is thermoneutral, the body is in a state of balance, neither using nor releasing energy to maintain its core temperature. However, when the environment is not thermoneutral, the body employs four heat transfer mechanisms to maintain homeostasis: conduction, convection, evaporation, and radiation. These mechanisms facilitate heat...
1.8K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
271
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
271


