纺织学报, 2026, 47(03): 175-183 doi: 10.13475/j.fzxb.20251102702

安全防护材料

面向智能设计的消防服热防护性能研究进展

张金凤1, 李嘉因1,2,3, 苏云,1,2,3, 田苗1,2,3, 李俊1,2,3

1 东华大学 服装与艺术设计学院, 上海 200051

2 东华大学 功能防护服装研究中心, 上海 200051

3 东华大学 现代服装设计与技术教育部重点实验室, 上海 200051

Advances in thermal protective performance of firefighter protective clothing for intelligent design

ZHANG Jinfeng1, LI Jiayin1,2,3, SU Yun,1,2,3, TIAN Miao1,2,3, LI Jun1,2,3

1 College of Fashion and Design, Donghua University, Shanghai 200051, China

2 Protective Clothing Research Center, Donghua University, Shanghai 200051, China

3 Key Laboratory of Clothing Design and Technology, Ministry of Education, Donghua University, Shanghai 200051, China

通讯作者: 苏云(1990—),男,副教授,博士。主要研究方向为功能防护服装设计及性能评估。E-mail: suyun150@dhu.edu.cn。

收稿日期: 2025-11-11   修回日期: 2026-02-6  

基金资助: 上海市经济和信息化委员会科学智能“百团百项”专项支持(2025-GZL-RGZN-BTBX-02014)
上海市教育委员会人工智能赋能科研计划资助(SMEC-AIDHUY-03)
中央高校基本科研业务费专项基金项目(2232026G-08)
东华大学“励志计划”资助项目(26D210702)

Received: 2025-11-11   Revised: 2026-02-6  

作者简介 About authors

张金凤(2001—),女,博士生。主要研究方向为功能与防护服装。

摘要

为从根本上提升火灾环境中消防员的安全保障水平,系统梳理了消防服热防护性能预测与设计方法的演进脉络,消防服热防护性能研究正在从以经验、理论、计算为核心的三大传统范式,向以数据驱动为特征的第四范式转变。首先分析了物理实验、数值模拟、计算流体力学模拟在应对复杂工况时的成本、周期及精度瓶颈。随后重点阐述了数据驱动方法如何为突破上述瓶颈提供可能,剖析了当前机器学习应用中存在的高保真数据稀缺、“黑盒”特性及泛化能力验证不充分的挑战。基于此提出未来研究的核心方向:深度融合物理信息、机器学习模型与先进AI算法,构建以多模态信息融合和物理知识增强为支柱的消防服智能设计体系。最后,展望了构建消防服数字孪生系统在实现智能优化设计与动态风险预警中的潜力,旨在为消防服的全流程智能化研发和人员安全保障体系的构建提供理论框架与发展路径。

关键词： 消防服; 热防护性能; 机器学习; 性能预测; 逆向设计

Abstract

Significance Firefighter protective clothing serves as a critical barrier for firefighters operating in extreme thermal hazard environments. Consequently, accurate prediction and optimization of the thermal protective performance of firefighter protective clothing present a core scientific challenge. The physical experiments provide direct performance test data, but their applications are restricted by destructive nature, high cost, long duration, and the difficulty in replicating complex dynamic conditions. Numerical simulations gain computational efficiency but face bottlenecks from their reliance on precise boundary conditions and high computational costs as models grow more complex. The combination of these bottlenecks necessitates a new research paradigm and data-driven machine learning provides promising solution. These algorithms enable learning of high-dimensional mapping relationships from large-scale experimental or simulation data. They could therefore predict outcomes without directly solving complex systems of heat and mass transfer differential equations. This data-driven approach demonstrates high possibility of effectively overcoming the efficiency and accuracy limitations that traditional methods face when dealing with complex dynamic conditions, and shows immense potential for performance assessment of firefighter protective clothing and the dynamic prediction of human burn injury risk.

Progress In machine learning algorithms, the attributes of data instances are referred to as ″features″. The input features cover three major dimensions, which are fire environment parameters, physical properties of fabrics, and human physiological indicators. The output response comprises quantitative measures of the performance of firefighter protective clothing, such as the second-degree skin burn time. Machine learning algorithms could refine the mapping relationship between input features and output responses, breaking through the limitation of linear assumptions. The data sources for machine learning algorithms are derived from physical experiments, literature compilations, and numerical simulations. The precise identification and engineering of key features help to improve the performance of machine learning models. The black-box nature of machine learning algorithms significantly reduces time costs and improves computational efficiency, but input data of poor quality may cause the model to produce biased results. The performance of these algorithms is evaluated based on the accuracy of prediction results, goodness of fit, and stability, with studies demonstrating that machine learning models outperform empirical equations. Furthermore, machine learning facilitates an emerging research direction, i.e. intelligent inverse design, which employs algorithms to find optimal fabric parameters that satisfy specific protective performance requirements. This approach offers a framework for the intelligent inverse design of firefighter protective clothing.

Conclusion and Prospect The prediction and design methods for the thermal protective performance of firefighter protective clothing are undergoing an evolutionary process, transitioning from physical experiments and numerical simulations toward data-driven and intelligent directions. At present, data-driven research has made practical advancements, but several challenges remain. First, collecting data from firefighters' live burn exercises involves high risks and substantial costs. Future research on the intelligent design of firefighter protective clothing can integrate experimentally validated high-fidelity numerical models or computational fluid dynamics heat transfer numerical simulations to generate virtual training data for multiple working conditions. Second, existing design paradigms lack a fully intelligent inverse design capability tailored to specific protection objectives. Future research could develop personalized inverse design platforms constrained by prior knowledge and driven by data. Finally, machine learning algorithms possess high application value in the areas of performance prediction for firefighter protective clothing and firefighter training. Exploring a synergistic pathway that combines ″physics-informed priors, data-driven models, and artificial intelligence agents″, and constructing digital twin systems, is expected to advance the design of firefighter protective clothing in a more precise, practical, and intelligent direction. This will provide key scientific support for development of intelligent firefighter protective clothing and next-generation safety assurance systems.

Keywords： firefighter protective clothing; thermal protective performance; machine learning; performance prediction; reverse design

PDF (9899KB) 元数据 多维度评价 相关文章 导出 EndNote| Ris| Bibtex  收藏本文

本文引用格式

张金凤, 李嘉因, 苏云, 田苗, 李俊. 面向智能设计的消防服热防护性能研究进展[J]. 纺织学报, 2026, 47(03): 175-183 doi:10.13475/j.fzxb.20251102702

ZHANG Jinfeng, LI Jiayin, SU Yun, TIAN Miao, LI Jun. Advances in thermal protective performance of firefighter protective clothing for intelligent design[J]. Journal of Textile Research, 2026, 47(03): 175-183 doi:10.13475/j.fzxb.20251102702

消防救援行动中的火灾环境具备严酷、复杂的特点:一方面会出现闪火等极端紧急事件,其热流密度可瞬时飙升至84 kW/m2;另一方面,消防员在常规救援作业中会持续暴露在5~12 kW/m2的热辐射环境中[1-2]。消防服是保障消防员在极端环境下安全作业的关键防护装备,对其热防护性能进行准确评估与优化设计,对于保障消防救援人员的人身安全、合理规划作业时长以及提升工作效能至关重要。采用传统实验与数值模拟方法开展的消防服相关研究,均依赖于边界条件与物性参数的合理设定。然而,简化火场复杂性会使传统方法遭遇精度瓶颈;在追求高保真火灾场景模拟的过程中,受限于工程周期与成本,传统方法难以高效指导消防服的优化设计。

2025年8月,国务院印发《关于深入实施“人工智能+”行动的意见》,明确指出“人工智能+”是信息技术革命的延续和深化[3]。人工智能(AI)领域的机器学习技术在新一轮科技革命中迅速发展。随着计算机算力的提升,数据驱动的研究方法已在高分子材料、生物医药等领域得到广泛应用。在消防服热防护性能预测与智能逆向设计研究中,该方法同样展现出显著的应用潜力。依托高质量实证数据集[4]和大规模数值模拟数据集[5],数据驱动方法可通过数据挖掘、特征重要性分析等手段,在无需构建复杂物理模型的情况下从数据中挖掘潜在规律[6],为消防服的智能设计开发提供了新方案。消防服研究正在从以经验、理论、计算为核心向以数据驱动为特征转变。

数据驱动的研究范式可整合多源物理实验和数值模拟数据[7],借助人工智能极大加快消防服设计与性能验证进程。有研究[8]将人工神经网络算法与多元线性回归经验方程的消防服热防护性能预测结果进行对比,结果表明,针对高度非线性、多变量的消防服热湿传递机制,机器学习算法相比经验方程具有更高的预测精度。然而,模型在特定数据集分布上验证的高精度,并不能保证在面对分布以外数据时依然稳定,提升模型泛化能力是当前面临的核心挑战。同时,由于火灾救援场景对于人员安全有高要求,亟需进一步发展兼具高泛化能力与物理解释性的算法研究。

目前,基于数据驱动的消防服研究仍面临诸多挑战,本文旨在梳理传统物理实验、一维数值模型与三维计算流体力学(CFD)传热模拟的研究进展,总结数据驱动的机器学习算法在消防服领域的实践探索及关键问题,并对未来融合多源数据、引入物理信息约束的智能化消防服设计发展方向提出设想。

1 物理驱动的性能评估

1.1 物理实验方法

小尺度台式测试从织物层面评估消防服热的防护性能,主要依据Stoll烧伤准则或Henriques皮肤烧伤积分模型[9],建立物理热传递过程与人体生理损伤之间的关联。标准化台式设备存在明显局限,其仅能模拟热辐射、热对流、接触热等较为单一的热源形式且样品放置采用平面式设计。为提升真实性,自开发设备研究逐渐向高温液体飞溅[10]、液-汽复合作用[11]等多模态热危害拓展,同时结合人体关节曲面[12]、持续出汗[13-14]及衣下空气层[15]等因素改进设备,热源强度也从固定模式扩展为可功率调节模式[16]。尽管如此,台式测试仍难以复现人体着装形态复杂的热传递过程。

全尺度假人系统从服装系统层面评估消防服局部与整体的热防护性能。针对火灾现场的极端热环境,目前主要存在燃烧假人和辐射假人2类模拟测试系统。其中,燃烧假人系统用于模拟热流密度84 kW/m2的瞬时闪火环境,定量分析人体穿着消防服时,皮肤烧伤分布、消防服形变等因素的综合作用[17-18]。辐射假人则用于模拟持续性热辐射环境导致的人体烧伤;相较于早期为暖体假人配置独立辐射热源的技术[19],现行系统通过集成增强型冷却装置、耐高温外壳以及自动化数据处理软件,显著提升了测试效率和精度。典型的辐射假人系统如美国北卡罗来纳州立大学的RadManTM可模拟5~21 kW/m2的热流密度,东华大学的热辐射假人Andi则适用于5 kW/m2以下的低热辐射环境研究,但能够更加准确地模拟人体热生理调节的影响。为关联不同尺度的测试结果,有研究[20]引入最大衰减因子作为关联指标,使得基于台式设备和假人测试的热防护性能结果具有可比性。全尺度假人实验能综合评估服装结构、合身度等设计因素和人体产热、出汗与行走等穿着效果对热防护性能的影响,但无法复现人体的动态生理调节,所支持的运动姿势和热流密度范围,也限制了实验方案的设置。

实战演练在受控火场中再现动态热流、烟雾及高强度活动的多因素耦合效应[21],基于人体的直接反馈评估消防员所需和可用安全作业时间[22],并建立物理暴露与主观感受的直接关联。此类研究指出消防员的烧伤高发区主要为肩、臂、关节弯曲处及受装备压迫部位[23],裸露皮肤的短时无损伤热暴露阈值约为2.3 kW/m2,而12 kW/m2的热流密度可能对人体造成致命伤害[24]。但演练环境难以标准化和复现,且成本高昂。气候舱实验在实验室模拟环境中进行,侧重于量化特定因素对人体生理及耐受极限的影响。研究发现,多数穿着热防护服的受试者可承受热流密度为2.0 kW/m2的热辐射3 min,而2.5 kW/m2及以上的暴露则应完全避免[25],此外,即便是低水平热辐射也会显著加剧中等强度运动下人体的热生理负荷与主观疲劳感[26],环境温度分布[27]和消防服的合身度[28]也对热生理具有显著影响。随着人工智能领域技术的发展,这些实证数据能校准高精度预测模型,以更安全和高效的方式实现消防服的性能预测与智能设计。

1.2 数值模型方法

针对火灾环境下消防员所处极端工况,一维传热传质数值模型假设热量沿服装厚度方向传递,将复杂火灾环境解构为外部热源、多层织物、衣下空气层及皮肤组织4个计算域,通过有限差分或有限体积法对描述各域内部及界面处传热传质过程的偏微分控制方程组进行求解[29],提供了参数化研究消防服热防护性能的方法,如图1所示。

图1

新窗口打开| 下载原图ZIP| 生成PPT

图1   数值模型计算域划分

Fig.1   Division of domain in numerical model


在数值模型的计算中,热源通常被简化为恒定的热通量或特定温度的100%辐射热源。对织物系统的建模从早期基于傅里叶定律的干态单层织物传热模型[30],发展到考虑多层织物层间热传导与热辐射的理论模型[31-32],再到集成水分蒸发、吸收、扩散乃至非线性润湿和剧烈相变的热湿耦合模型[33-34],其模拟的物理机制日益复杂。对衣下空气层的建模也从厚度固定的静态层假设[35],发展出用正弦函数描述匀速运动引发的空气层周期性变化[36-37],现已演进出能够反映消防员非匀速运动和姿态变化的传热模型[38]。对皮肤组织的损伤评估也从Pennes经典生物传热方程发展到更适用于模拟闪火等短时高热流场景的双相滞后生物传热模型[39]与考虑消防员年龄和身体部位生理差异的个体化模型[40]。但目前多数模型忽略了材料在高温下的热解炭化,即假设服装热物理性质为恒定值[41],这可能导致消防服热防护性能的预测结果偏高。

基于数值模型的计算流体动力学(CFD)方法补充了对复杂几何曲面和流体运动的模拟,通过热场云图、皮肤烧伤分布图等可视化手段直观呈现热防护效果[42],其人体和服装的几何模型从简化的同心圆柱体[43]发展到基于真实扫描数据、逆向工程与简化算法的三维人体着装模型[44],对于衣下空气层与服装合体性的模拟也逐渐完善[45]。现已应用于石化火炬[46]、油罐火灾[47]、强风火灾[48]等救援场景的仿真,通过对比火灾热流场与着装人体能承受的热流密度阈值,计算消防员的安全热暴露距离。此外,也有研究者利用激光雷达技术收集植被、火焰及地形的实时数据[49-50],采用内嵌三维火灾模型的专用软件工具[51]预测消防员的安全距离,但由于对火灾场景的简化,其预测准确度还有待验证。

2 数据驱动的性能预测

2.1 机器学习算法

基于统计分析建立的经验方程往往以线性关系描述环境、服装参数与消防服热防护性能之间的内在规律。机器学习算法则利用数据驱动提炼输入特征与输出响应之间的映射关系,突破线性假设的限制。已有研究[52-53]表明,机器学习算法在预测消防服热防护性能时准确率和泛化能力均优于经验方程,为消防服优化设计提供了新范式,如图2所示。

图2

新窗口打开| 下载原图ZIP| 生成PPT

图2   消防服性能评估及优化设计的研究范式

Fig.2   Research paradigms for performance evaluation and optimization design of firefighter protective clothing


在机器学习算法中,将数据实例的属性称为“特征”,经筛选后的特征将作为机器学习模型的输入。早期研究如朱根娣等[54]探索了径向基函数在预测消防服热防护性能中的应用,但未考量织物特征。随后,Udayraja等[55]构建的人工神经网络模型则将单层热防护织物的性能作为关键输入特征。Mandal等[56]进一步将特征维度扩展至多层织物系统,并首次将汗液等人体热湿耦合作用相关因素加入输入特征。Rajput等[5]将与火灾环境下消防服系统热湿传递相关的物理参数扩充至23个,验证了高维多源特征对提升预测精度的有效性。如表1所示,当前研究所选的输入特征涵盖火灾环境参数、织物物理性能及人体生理指标三大维度。其中,织物厚度、密度、面密度、热阻、湿阻以及环境热流密度等输入特征受到普遍关注。输出响应主要为皮肤烧伤时间等消防服性能量化指标,但由于火灾环境中人体生理参数的获取具有极大的挑战性,此类高价值特征的使用仍相对匮乏。

表1   火灾环境消防服性能机器学习算法对比分析

Tab.1  Comparative analysis of machine learning algorithms for evaluating the performance of firefighter protective clothing under fire conditions

文献算法输入特征输出响应模型效能
[54]径向基函数神经网络环境热流密度,热暴露时间;消防服TPP值皮肤Ⅱ级烧伤时间RE<9.3%
[55]人工神经网络环境热流密度;单层织物组成成分、
经纬密、厚度;
衣下空气层厚度		皮肤Ⅱ级烧伤时间RE<3.565 8%;
σ<0.047 8
[56]人工神经网络环境热流密度;多层织物组成成分、
面密度、厚度、热阻、透气性、
湿阻、液体扩散速度		织物热防护性综合指标R2=0.99;
RMSE=0.71
热生理舒适性综合指标R2=0.94;
RMSE=1.53
[57]多层感知机
神经网络		织物结构、线密度、经纬密、面密度、
厚度、极限氧指数、湿阻		EN 367标准/ISO 6942
标准下升温12 ℃/
24 ℃各自所需时间		MAPE<6.87%;
r>0.83
[4]人工神经网络织物组成成分、结构、经纬密、面密度、
厚度、透气性、热阻、湿阻、
湿润程度;是否存在衣下空气层		热传递性能指标r=0.54;
RMSE=4.37
总热损失r=0.33;
RMSE=293.03
[5]人工神经网络多层织物厚度、经纬密、导热系数、比热容;
固体纤维体积分数、回潮率、湿润程度、液体
扩散系数;衣下空气层厚度;基于上述物理参
数量纲分析得到17个无量纲参数		皮肤Ⅱ级烧伤时间RE<10%;
RMS<0.001;
R2=0.972 3

注:RE为相对误差;σ为预测误差分散度;R2为决定系数;RMSE为均方根误差;MAPE为平均绝对百分比误差;r为Pearson相关系数;RMS为均方误差。

新窗口打开| 下载CSV


2.2 数据集构建与特征工程

由于火灾救援实战演练与气候舱实验在伦理、成本与可复现性上的固有挑战,反映真实火场暴露及人体生理响应的数据极为稀缺。数据驱动的消防服性能预测研究主要依赖3类数据来源:物理实验、文献汇编和数值模拟。其中,普遍采用标准化实验室测试获取少数特定织物系统的热物理性能参数和热防护性能[4,56-57],但样本规模较小,模型的泛化能力与预测精度受限。整合多个已发表的独立实验数据可构建样本规模超过单一实验的数据库[55],近年,亦有研究采用经过验证的数值模型系统性生成包含10 000个样本的大规模数据集[5],提供了突破物理实验数据规模和多样性局限的方案。

样本特征过少难以全面反映多因素耦合作用下的热湿传递机制;而样本规模有限时,特征过多会增加计算负担,导致过拟合并降低泛化能力。最优特征数量尚未有明确结论,对关键特征的精准识别与工程化处理是提升模型效能的关键。数据清洗是处理异常值、实现数据标准化处理的基础方法,特征选择与降维能进一步提取关键特征,量化其对热防护性能的影响权重。有研究[52]借助随机森林算法进行特征重要性评估,识别出热流密度是显著影响皮肤烧伤的关键特征;亦有研究[58]应用Buckingham π定理识别参数和防护服系统内热湿传递函数间的关系,将大量物理特征降维为无量纲参数组,以增强模型在有限数据条件下的泛化能力[5]。

未来研究可将经实验验证的高保真数值模拟和CFD传热模拟共同作为数据增广手段,构建覆盖数据、文本、图像的多工况训练样本,扩充样本规模,为数据驱动模型提供更充分的泛化依据。

2.3 物理可解释性

当前研究采用的自监督学习模型通过从历史数据中捕捉潜在规律以进行预测,本质上属于高维非线性映射函数。由于其从输入到输出的决策过程缺乏透明、直观的物理逻辑,其预测过程常被视作“黑箱”。这类机器学习算法在引入新变量时无需重构整个模型,显著降低了时间成本并提升了运算效率[59-60]。然而,其“黑箱”特性也导致模型结果的可解释性较传统经验方程有所不足,如果输入数据质量较差可能导致模型得出具有偏见性的结果,使其在安全防护领域难以得到完全信任。当模型预测与物理直觉或实验结果相悖时,“黑箱”特性使得追溯与诊断错误根源变得困难,从而限制了模型在新材料研发中的指导价值。

当前研究主要通过特征转换对现有特征进行组合变换生成新指标,以增强模型的解释性与实用价值。朱根娣等[54]对原有环境和织物特征参数进行计算得到消防服热防护性能值(TPP)作为关键参数;Mandal等[56]则构建了基于织物降温速率与热阻的热生理舒适性综合指标和基于皮肤温度升高时间计算得到的热防护性能综合指标,并将其作为输出响应。未来研究可转向物理可解释性更高的“灰箱”或“白箱”模型,将领域内的物理定律、先验知识或物理模型的输出作为信息融入到模型中,以提高模型的准确性和可解释性,为消防服的智能设计提供更深层的科学依据。

2.4 模型效能

机器学习算法的效能评估主要围绕预测结果的准确性(RMSE、RE、MAPE)、拟合优度(R2)和稳定性(r、σ)展开[4,55]。模型效能的提升与算法选择及参数配置密切相关。算法层面,随机森林、核函数支持向量机、正则化逻辑回归等具有控制数据中的高维度和噪声的能力的算法通常能获得更高的准确性,但其计算成本也更高[60]。此外,对于神经网络而言,其预测准确性会随着隐含层数量和样本集规模的提升而上升[54]。

尽管当前模型预测与物理实验间还存在一定偏差,但现有研究中机器学习算法的整体性能已初步验证了该方法的可行性与先进性。为真正推动模型从实验室标准测试走向复杂火场环境应用,未来的研究需建立更严格的交叉验证与评估体系以更客观地评价模型的泛化性能。

3 数据驱动的智能逆向设计

传统消防服的设计依赖于物理实验的试错和调整以优化性能,随着数值模型和数据驱动模型的发展,研究者可以在虚拟环境中高效地对服装性能进行评估,属于织物系统热湿传递正问题的求解。在正问题的基础上,数据驱动的机器学习算法拓展出一种更加主动的消防服逆向设计方法,即:使用搜索算法,逆向获取满足特定防护性能要求的最优织物参数,这种纺织材料的智能逆向设计方法,在数学上被称为参数决定反问题[61]。

在中性热环境或低温环境下设计的反问题往往以满足特定热舒适性为指标[62],然而在火灾环境下,消防服很难完全满足人体的舒适性要求,同时,保证消防员的人身安全是救援任务中更为重要的目标。因此,火灾环境织物参数决定反问题通常被构建为在保证不发生二级皮肤烧伤的前提下,寻求最大化安全工作时间所对应的织物参数组合[63-64]。这既包括对于单个织物参数的最优值求解的单参数决定反问题[65],也包括寻求多个关键物理量最优组合的多参数同时决定反问题[66]。例如,在多层消防服的结构设计中,可以通过智能逆向算法,在限定总重量的前提下,精准计算出外层、防水透气层与隔热层三者之间的最优厚度配比;或者针对外层材料开发,逆向推导PBI与Kevlar等高性能纤维的最佳混纺比例,以实现热稳定性与力学强度的最佳平衡。对于单个热防护性能目标,可能存在多种解决方案,通过对多组候选方案进行排序与筛选,可应对一对多映射关系的非唯一性,并确定最优设计;也可能不存在解决方案[67],此时如果允许目标少量变化可能会大大提高模型的实用性,并允许找到可能的解决方案。

随着技术快速迭代,人工智能的应用形态不断拓展。大语言模型、AI智能体等高交互性的生成式技术亦开始在材料设计领域显现潜力。已有研究[68]将材料参数视为自然语言训练大模型,使其具有根据自然语义进行推理与逆向设计运算的能力。AI赋能的消防服性能预测与逆向设计方案可以参考软体机器人领域[69],从多模态信息融合、物理信息约束增强、实时响应策略3个方面开展。综合运用经验证的数值模拟技术,获取大样本仿真数据对模型进行预训练,利用高质量物理实验数据对模型进行微调,实现多模态信息的融合,使模型在实验室数据样本和实战演练数据样本上具备更好的表达;向机器学习算法模型引入描述热质传递的偏微分方程作为约束,确保模型能做出符合物理直觉的热防护性能预测和根据热防护目标输出满足需求的消防服具体物理参数;耦合生成式技术,构建火灾场景数字孪生系统与消防服智能设计平台,向着多模态融合与全流程智能化的方向深度演进。

4 结束语

消防服热防护性能的预测和设计方法正经历着从物理实验、数值模拟向数据驱动、智能化方向演进的过程。针对消防员实战演练数据采集风险大、成本高,物理实验难以完全复现复杂动态工况的问题,未来消防服智能设计可整合经验证的高保真数值模型或CFD传热数值模拟,生成多工况的虚拟训练数据,从根本上扩充数据集,为数据驱动模型提供物理信息约束。

现有消防服设计模式缺乏面向特定防护目标的全流程智能化的逆向设计能力。未来研究可构建由先验知识约束、数据驱动的个性化逆向设计平台。利用AI智能体理解自然语言描述的设计需求,自主调用仿真工具进行性能预测与方案迭代,高效探索能满足特定场景与个体需求的消防服设计方案,推动消防服设计范式从正向预测向全流程智能化逆向设计发展。

数据驱动模型在构建消防员数字孪生系统方面应用价值较高,但存在物理可解释性不足的风险。未来研究可通过构建由物理信息约束的消防员数字孪生系统,提升仿真模拟的可靠性,为消防服的研发提供高可信度的虚拟测试。结合VR/AR等沉浸式体验技术,也有望为消防员提供无风险的实战演练,持续推动消防服设计向更加精准、智能、实用的方向发展,为消防服的智能化研发与消防员安全保障体系的构建提供关键科学支撑。

参考文献

KRASNY J, ROCKETT J A, HUANG D Y.

Protecting fire fighters exposed in room fires: comparison of results of bench scale test for thermal protection and conditions during room flashover

[J]. Fire Technology, 1988, 24(1): 5-19.

DOI:10.1007/BF01039637      URL     [本文引用: 1]

ROSSI R.

Fire fighting and its influence on the body

[J]. Ergonomics, 2003, 46(10): 1017-1033.

PMID:12850937      [本文引用: 1]

Working conditions for fire fighters can be described according to the environment temperature and the incident radiant heat flux. Measurements for this study in buildings for fire fighting training have shown that fire fighters are typically exposed to radiant heat fluxes of between 5 and 10 kWm(-2) during this kind of exercise. The heat load can nevertheless be much higher. In one case, 42 kWm(-2) was measured. The temperatures reached between 100 and 190 degrees C at 1 m above ground, going up to 278 degrees C in one case. Human trials have been performed with 17 fire fighters. After exercises (about 15 min) in a heated room, the mean core temperature of the fire fighters rose by 0.6 degrees C with a surrounding temperature of 31 degrees C and 1.0 degrees C with 38 degrees C. The sweat production varied from 0.7 to 2.1 lh(-1); 16% to 45% of sweat remained in the clothing layers. During the exercises in the training buildings, a mean of 48 degrees C has been measured between fire fighters' clothing and workwear. These conditions lead to an increase of the relative humidity in all the jackets up to 100%. When the fire fighters came out of the fire, the humidity remained at this level in the PVC coated jackets while it was in some cases strongly reduced in breathable jackets.

国务院关于深入实施“人工智能+”行动的意见

[EB/OL]. 国务院公报, 2025-08-21, [2025-11-06]. https://www.gov.cn/gongbao/2025/issue_12266/202509/content_7039598.html.

URL     [本文引用: 1]

Opinions of The State Council on Deepening the Implementation of the ″Artificial Intelligence Plus″ Action

[EB/OL]. Gazette of the State Council of the People's Republic of China, 2025-08-21, [2025-11-06]. https://www.gov.cn/gongbao/2025/issue_12266/202509/content_7039598.html.

URL     [本文引用: 1]

MANDAL S, MAZUMDER N U S, AGNEW R J, et al.

Using artificial neural network modeling to analyze the thermal protective and thermo-physiological comfort performance of textile fabrics used in oilfield workers' clothing

[J]. International Journal of Environmental Research and Public Health, 2021, 18(13): 6991.

DOI:10.3390/ijerph18136991      URL     [本文引用: 4]

Most of the fatalities and injuries of oilfield workers result from inadequate protection and comfort by their clothing under various work hazards and ambient environments. Both the thermal protective performance and thermo-physiological comfort performance of textile fabrics used in clothing significantly contribute to the mitigation of workers’ skin burns and heat-stress-related deaths. This study aimed to apply the ANN modeling approach to analyze clothing performance considering the wearers’ sweat moisture and the microclimate air gap that is generated in between their body and clothing. Firstly, thermal protective and thermo-physiological comfort performance of fire protective textiles used in oilfield workers’ clothing were characterized. Different fabric properties (e.g., thickness, weight, fabric count), thermal protective performance, and thermo-physiological comfort performance were measured. The key fabric property that affects thermal protective and thermo-physiological performance was identified as thickness by statistical analysis. The ANN modeling approach could be successfully implemented to analyze the performance of fabrics in order to predict the performance more conveniently based on the fabric properties. It is expected that the developed models could inform on-duty oilfield workers about protective and thermo-physiological comfort performance and provide them with occupational health and safety.

RAJPUT B, SHARMA S, RAY B, et al.

Performance prediction of flame-retardant clothing using correlations and artificial neural networks: optimizing firefighter safety

[J]. International Communications in Heat and Mass Transfer, 2024, 159: 108324.

DOI:10.1016/j.icheatmasstransfer.2024.108324      URL     [本文引用: 5]

MANDAL S, ANNAHEIM S, GREVE J, et al.

Modeling for predicting the thermal protective and thermo-physiological comfort performance of fabrics used in firefighters' clothing

[J]. Textile Research Journal, 2019, 89(14): 2836-2849.

DOI:10.1177/0040517518803779      URL     [本文引用: 1]

\n Standardized test methods are available for measuring the thermal protective as well as thermo-physiological comfort Performance of fabrics used in firefighters' clothing. However, these tests are usually fabric destructive in nature, time consuming, and/or expensive to carry out on a regular basis. Hence, the availability of empirical models could be useful for conveniently predicting the thermal protective and thermo-physiological comfort performances from the fabric properties. The aim of this study is to develop individual models for predicting thermal protective and thermo-physiological comfort performances of fabrics. For this, different single- and multi-layered fabrics that are commercially used to manufacture firefighters' protective clothing were selected, and the fundamental properties of these fabrics (weight, thickness, thermal resistance, air-permeability, evaporative resistance, and water spreading speed) were measured using the standard test methods developed by the International Organization for Standardization (ISO) or the American Association of Textile Chemists and Colorists. The thermal protective performance of these fabrics was measured by the ISO 9151:2016 test method under 80 kW/m\n 2\n flame exposure. The thermo-physiological comfort performance of fabrics was determined by the ISO 18640-1:2018 test method and a statistical model. Thereafter, the key fabric properties affecting the thermal protective and thermo-physiological comfort performances of fabrics were determined statistically. It has been found that thermal and evaporative resistances are the key fabric properties to affect the thermal protective performance, whereas the fabric weight, evaporative resistance, and water spreading speed are the key properties to affect the thermo-physiological comfort performance. By employing these key fabric properties, Multiple Linear Regression and Artificial Neural Network (ANN) models were developed for predicting the thermal protective and thermo-physiological comfort performances. Through a comparison of the predicting performance parameters of these models, it has been found that ANN models can more accurately predict the performances of fabrics. These models can be implemented in the textile industry and academia for effectively and conveniently predicting the thermal protective and thermo-physiological comfort performances only by utilizing the key fabric properties.\n

YIN W J, LIU M, GONG X G.

Paradigm shift in materials science driven by artificial intelligence: methods, platforms, and frontiers of applications

[J]. Chinese Science Bulletin, 2025, 70(24): 4012-4014.

[本文引用: 1]

MANDAL S, SONG G W, ROSSI R M, et al.

Characterization and modeling of thermal protective fabrics under Molotov cocktail exposure

[J]. Journal of Industrial Textiles, 2022, 51(1_suppl): 1150S-1174S.

[本文引用: 1]

HENRIQUES F C, MORITZ A R.

Studies of thermal injury: I. the conduction of heat to and through skin and the temperatures attained therein. a theoretical and an experimental investigation

[J]. The American Journal of Pathology, 1947, 23(4): 530-549.

[本文引用: 1]

卢业虎. 高温液体环境下热防护服装热湿传递与皮肤烧伤预测[D]. 上海: 东华大学, 2013:31-47.

[本文引用: 1]

LU Yehu. Study on heat and mass transfer of thermal protective clothing and prediction of skin burn upon hot liquid splashes[D]. Shanghai: Donghua University, 2013:31-47.

[本文引用: 1]

SU Y, LI J.

Development of a test device to characterize thermal protective performance of fabrics against hot steam and thermal radiation

[J]. Measurement Science and Technology, 2016, 27(12): 125904.

DOI:10.1088/0957-0233/27/12/125904      URL     [本文引用: 1]

SU Y, LI R, YANG J, et al.

Developing a test device to analyze heat transfer through firefighter protective clothing

[J]. International Journal of Thermal Sciences, 2019, 138: 1-11.

DOI:10.1016/j.ijthermalsci.2018.12.031      URL     [本文引用: 1]

ZHANG W H, SU Y, LI J.

Influences of moisture management performance and continuous sweat rate on heat transfer through firefighting clothing under radiant exposure

[J]. International Journal of Thermal Sciences, 2023, 192: 108401.

DOI:10.1016/j.ijthermalsci.2023.108401      URL     [本文引用: 1]

ZHANG W H, SU Y, LI J.

Developing a test device to analyze heat transfer combined with radiant exposure and continuous liquid sweating through thermal protective clothing

[J]. Journal of Industrial Textiles, 2023, 53: 15280837231177870.

[本文引用: 1]

王琦, 田苗, 苏云, 等.

开放/封闭空气层对阻燃织物热防护性能的影响

[J]. 纺织学报, 2020, 41(12): 54-58.

DOI:10.13475/j.fzxb.20200303105      [本文引用: 1]

为探究衣下空气层间的传热方式对阻燃织物外观性能和阻燃织物系统传热机制的影响,基于热防护性能(TPP) 实验装置,构建开放式和封闭式空气层以模拟实际着装时“服装-人体皮肤”的空间关系。利用彩色图像处理方法对比热暴露前后的织物外观和热收缩情况,从能量传递、TPP值和二级烧伤时间角度评估“织物-空气层”系统的传热特性和热防护性能。结果表明:空气层的介入会降低热传递效率,进而提升阻燃织物的热防护性能,但会加速织物老化,加剧织物热收缩;当打开空气层与周围环境热量交换的通路时,空气层间热量的流动路径变复杂,且织物的热防护性能进一步提升。

WANG Qi, TIAN Miao, SU Yun, et al.

Effect of open/closed air layer on thermal protective performance of flame-resistant fabrics

[J]. Journal of Textile Research, 2020, 41(12): 54-58.

DOI:10.13475/j.fzxb.20200303105      [本文引用: 1]

To investigate the effects of heat transfer modes on appearance and thermal protective performance of thermal protective clothing with an air layer, the thermal protective performance (TPP) tester was established to simulate the actual spatial relationship between the human skin and garment with an open or closed air layer. Color image processing was used to evaluate the shrinkage of the fabrics before and after the heat exposure. The heat transfer and thermal protective performance of the “fabric-air layer” system were evaluated from the perspectives of energy transfer, TPP value and second degree burn time. Experimental results reveal that the presence of air layer decreases the heat transfer efficiency and improves the thermal protective performance of the flame-resistant fabrics. However, it also accelerates the aging and thermal shrinkage of the fabrics. When the heat exchange path between the air layer and the surrounding environment is opened, the fluid flow of heat within the air space becomes much sophisticated, and the thermal protective performance of fabric is further improved.

胡建锋, 朱方龙, 冯倩倩, 等.

织物热防护性能测试方法比较

[J]. 印染, 2019, 45(23): 47-52.

[本文引用: 1]

HU Jianfeng, ZHU Fanglong, FENG Qianqian, et al.

Comparisons among thermal protection performance test methods for fabrics

[J]. China Dyeing and Finishing, 2019, 45(23): 47-52.

[本文引用: 1]

李俊, 翟丽娜, 王敏, 等.

闪火中防护服装的形变及其影响因素

[J]. 纺织学报, 2014, 35(1): 95-101.

[本文引用: 1]

防火服在火焰中的收缩形变会影响其热防护性能并制约人体的肢体运动。本文提出用捺印的方法，通过燃烧假人闪火燃烧试验研究防火服各部位形变量的分布规律，探究形变差异的原因及影响因素，对比分析服装形变与假人皮肤表面烧伤程度的关系。结果显示，燃烧试验后防火服在四肢和背部发生了显著收缩形变，热流量、衣下空气层等是主要影响因素。着装姿势越复杂、闪火持续时间越长，服装越宽松，服装面料的面密度越大，服装形变越显著。服装形变显著的对应部位衣下皮肤的烧伤也越严重。

LI Jun, ZHAI Lina, WANG Min, et al.

Shrinkage of fire-fighting suit during flash fire exposure

[J]. Journal of Textile Research, 2014, 35(1): 95-101.

[本文引用: 1]

The shrinkage of fire protective clothing may affect its thermal performance and block body movement. In this paper, by using an instrumented mannequin, flame-test for complete garments is applied to simulate the fire situation. Seals marked on the garment are used to measure the shrinkage distribution of garments during flash fire exposure. The reasons for the shrinkage and its factors are studied. The relationship between shrinkage and the burn injury of manikin skin is preliminarily analyzed. Results show that the sleeves, trousers and the back of the clothing shrink significantly. The variation of the shrinkage results from the heat flux, air gap and other factors. The shrinkage extent is influenced by wearing posture, fire duration, construction size, and fabric density. As a whole, burn injury will be more serious where the shrink is more significant.

田苗, 苏云, 李俊.

“火灾环境-防护服-人体” CFD传热模拟及皮肤烧伤分布预测

[J]. 清华大学学报(自然科学版), 2024, 64(6): 1032-1038.

[本文引用: 1]

TIAN Miao, SU Yun, LI Jun.

Simulating heat transfer from the fire environment to protective clothing and the human body using CFD and predicting skin burn distribution

[J]. Journal of Tsinghua University (Science and Technology), 2024, 64(6): 1032-1038.

[本文引用: 1]

BRÖDE P, KUKLANE K, CANDAS V, et al.

Heat gain from thermal radiation through protective clothing with different insulation, reflectivity and vapour permeability

[J]. International Journal of Occupational Safety and Ergonomics, 2010, 16(2): 231-244.

PMID:20540842      [本文引用: 1]

The heat transferred through protective clothing under long wave radiation compared to a reference condition without radiant stress was determined in thermal manikin experiments. The influence of clothing insulation and reflectivity, and the interaction with wind and wet underclothing were considered. Garments with different outer materials and colours and additionally an aluminised reflective suit were combined with different number and types of dry and pre-wetted underwear layers. Under radiant stress, whole body heat loss decreased, i.e., heat gain occurred compared to the reference. This heat gain increased with radiation intensity, and decreased with air velocity and clothing insulation. Except for the reflective outer layer that showed only minimal heat gain over the whole range of radiation intensities, the influence of the outer garments' material and colour was small with dry clothing. Wetting the underclothing for simulating sweat accumulation, however, caused differing effects with higher heat gain in less permeable garments.

HE J Z, WANG M, LI J.

Determination of the thermal protective performance of clothing during bench-scale fire test and flame engulfment test: evidence from a new index

[J]. Journal of Fire Sciences, 2015, 33(3): 218-231.

DOI:10.1177/0734904115581620      URL     [本文引用: 1]

WILLI J M, HORN G P, MADRZYKOWSKI D.

Characterizing a firefighter's immediate thermal environment in live-fire training scenarios

[J]. Fire Technology, 2016, 52(6): 1667-1696.

DOI:10.1007/s10694-015-0555-1      URL     [本文引用: 1]

ZHANG Y X, ZHANG X N, HUANG X Y.

Design a safe firefighting time (SFT) for major fire disaster emergency response

[J]. International Journal of Disaster Risk Reduction, 2023, 88: 103606.

DOI:10.1016/j.ijdrr.2023.103606      URL     [本文引用: 1]

ALLEN J, CORRADO S, COX D, et al.

Thermal Capacity of Fire Fighter Protective Clothing

[R]. Quincy: Fire Protection Research Foundation, 2008: 1-35.

[本文引用: 1]

STOLL A M, GREENE L C.

Relationship between pain and tissue damage due to thermal radiation

[J]. Journal of Applied Physiology, 1959, 14(3): 373-382.

PMID:13654166      [本文引用: 1]

HEUS R, KINGMA B R M, VAN BERLO B M A, et al.

The protective performance of process operators' protective clothing and exposure limits under low thermal radiation conditions

[J]. Biology, 2022, 11(8): 1222.

DOI:10.3390/biology11081222      URL     [本文引用: 1]

ZHANG S, ZHU N, LU S L.

Responses of human perception and skin temperature to directed thermal radiation in hot environments

[J]. Building and Environment, 2021, 197: 107857.

DOI:10.1016/j.buildenv.2021.107857      URL     [本文引用: 1]

GENG J, GU Y, WENG W G, et al.

A multi-segmented human bioheat model for asymmetric high temperature environments

[J]. International Journal of Environmental Research and Public Health, 2022, 19(22): 15259.

DOI:10.3390/ijerph192215259      URL     [本文引用: 1]

FONTANA P, SAIANI F, GRÜTTER M, et al.

Thermo-physiological impact of different firefighting protective clothing ensembles in a hot environment

[J]. Textile Research Journal, 2018, 88(7): 744-753.

DOI:10.1177/0040517516688629      URL     [本文引用: 1]

It is currently unclear how the assembly of different fabric layers of personal protective clothing (PPC) contributes to differences in thermal comfort among garments. Therefore, we used two different approaches to investigate the effect of PPC on body heat dissipation: a technical characterization of textiles (using sweating Torso methodology) and thermo-physiological wearing trials. We hypothesized that the technical characterization provides a similar outcome compared to the wearing trials and, thus, proves to have high thermo-physiological relevance.

SONG G W, CHITRPHIROMSRI P, DING D.

Numerical simulations of heat and moisture transport in thermal protective clothing under flash fire conditions

[J]. International Journal of Occupational Safety and Ergonomics, 2008, 14(1): 89-106.

PMID:18394330      [本文引用: 1]

A numerical model of heat and moisture transport in thermal protective clothing during exposure to a flash fire was introduced. The model was developed with the assumption that textiles are treated as porous media. The numerical model predictions were compared with experimental data from different fabric systems and configurations. Additionally, with the introduction of a skin model, the parameters that affect the performance of thermal protective clothing were investigated.

TORVI D A, ENG P, THRELFALL T G.

Heat transfer model of flame resistant fabrics during cooling after exposure to fire

[J]. Fire Technology, 2006, 42(1): 27-48.

DOI:10.1007/s10694-005-3733-8      URL     [本文引用: 1]

SU Y, HE J Z, LI J.

An improved model to analyze radiative heat transfer in flame-resistant fabrics exposed to low-level radiation

[J]. Textile Research Journal, 2017, 87(16): 1953-1967.

DOI:10.1177/0040517516660892      URL     [本文引用: 1]

An improved heat transfer model, based on the two-flux model, in a multilayer flame-resistant fabric system with an air gap was proposed. The developed model considered the thermal radiation by absorbing, transmitting, emitting and reflecting in porous fabrics. The predicted results of the new model were compared with the previous Beer’s law model and the experimental results, and were found to be in good agreement with the experimental ones. The aim of this study is to investigate the mechanism of radiant heat transfer in the multilayer fabric system and the effects of the optical properties of flame-resistant fabric on heat transfer in the fabric system. The numerical results demonstrated that the self-emission in multilayer fabric system increases not only the rate of thermal energy transferred to human skin during thermal exposure, but also the rate of thermal energy transmitting to the ambience during cooling. The fabric’s optical properties have a complex influence on the transmitted and stored energy in multilayer protective clothing. The finding obtained in this study can provide references for the improvement of the thermal protective performance of flame-resistant fabrics.

DAS A, ALAGIRUSAMY R, KUMAR P.

Study of heat transfer through multilayer clothing assemblies: a theoretical prediction

[J]. AUTEX Research Journal, 2011, 11(2): 54-60.

DOI:10.1515/aut-2011-110205      URL     [本文引用: 1]

MALAQUIAS A F, CAMPOS J B L M.

Sudden water exposure on geared firefighters may cause unexpected burns in post-fire periods

[J]. Thermal Science and Engineering Progress, 2024, 49: 102452.

DOI:10.1016/j.tsep.2024.102452      URL     [本文引用: 1]

CHITRPHIROMSRI P, KUZNETSOV A V.

Modeling heat and moisture transport in firefighter protective clothing during flash fire exposure

[J]. Heat and Mass Transfer, 2005, 41(3): 206-215.

[本文引用: 1]

GHAZY A.

Numerical study of the air gap between fire-protective clothing and the skin

[J]. Journal of Industrial Textiles, 2014, 44(2): 257-274.

DOI:10.1177/1528083713483784      URL     [本文引用: 1]

The analysis of the air gap between fire-protective clothing and the skin plays a crucial role in evaluating the protective performance of the clothing. However, the more accurate the analysis of the air gap, the more complex the air-gap model. This article introduces a novel air-gap model that stands halfway in terms of accuracy and complexity between other two models that already exist in the literature. A comparison between the performances of fire-protective clothing predicted by using the three air-gap models is discussed in this article. Different parameters that affect heat transfer within the air gap and hence the protective performance of the clothing were studied to assess the novel air-gap model compared with the other two models. Despite its simplicity, the novel air-gap model predicted the performance of fire-protective clothing as accurately as the most realistic model.

GHAZY A.

Influence of the fabric properties on the protective performance of flame resistant clothing during the body movement

[J]. Fire Technology, 2019, 55(3): 713-728.

DOI:10.1007/s10694-018-0802-3      [本文引用: 1]

LEI Y, WANG F M, YANG J.

An extended model for analyzing the heat transfer in the skin-microenvironment-fabric system during firefighting

[J]. Materials, 2023, 16(2): 487.

DOI:10.3390/ma16020487      URL     [本文引用: 1]

This study proposed an extended multi–layer heat transfer model to simulate skin burns of firefighters during firefighting. The proposed model takes into account the effect of fabric movement frequencies, fabric movement amplitudes and human body movement speeds on the heat transfer between the skin and the heat source under low–level radiative exposure. The simulation performance was validated against the simulations in the published literature in terms of the heat transfer in the multi–layer fabric system, skin temperature and skin burns. The results indicated that the fabric periodic movement caused by human body movement decreased the time to skin burns and the skin temperature increased with increasing fabric movement amplitude. During firefighting, the time to 2nd degree burn was 33.3–35.2% shorter at medium human body movement speed than at low and high movement speeds. Furthermore, at low movement speeds, the time to 2nd degree burn was negatively associated with fabric movement amplitude, whereas it was delayed by 12.9–29.8% at the fabric movement amplitude of 2.5 mm at medium and high human body movement speeds. This research provides foundational knowledge for the development of a new generation of firefighters’ protective clothing (FPC) and the assessment of skin burns in firefighters.

ACHARYA J, BHANJA D, MISRA R D.

Prediction of safe zone for firefighters exposed to purely radiant heat source: a numerical analysis

[J]. International Journal of Thermal Sciences, 2023, 190: 108302.

DOI:10.1016/j.ijthermalsci.2023.108302      URL     [本文引用: 1]

UDAYRAJ, TALUKDAR P, ALAGIRUSAMY R, et al.

Heat transfer analysis and second degree burn prediction in human skin exposed to flame and radiant heat using dual phase lag phenomenon

[J]. International Journal of Heat and Mass Transfer, 2014, 78: 1068-1079.

DOI:10.1016/j.ijheatmasstransfer.2014.07.073      URL     [本文引用: 1]

ACHARYA J, BHANJA D, MISRA R D.

Investigating the protective performance of turnout gears for firefighters under diverse exposure conditions: effect of age and body segments

[J]. Thermal Science and Engineering Progress, 2024, 50: 102543.

DOI:10.1016/j.tsep.2024.102543      URL     [本文引用: 1]

UDAYRAJ, WANG F M.

A three-dimensional conjugate heat transfer model for thermal protective clothing

[J]. International Journal of Thermal Sciences, 2018, 130: 28-46.

DOI:10.1016/j.ijthermalsci.2018.04.005      URL     [本文引用: 1]

陈慧臻, 戴宏钦, 潘姝雯, 等.

计算流体力学在服装传热性能评价中的应用

[J]. 现代纺织技术, 2022, 30(2): 18-26.

DOI:10.19398/j.att.202103026      [本文引用: 1]

为突破传统实验手段与一维数学模型的局限,一些研究者提出基于计算流体力学模拟人体-服装-环境系统的热量流动与传递过程,通过计算皮肤温度、传热系数等参数的方式评价服装的传热性能。文章概述了仿真方法解决服装传热问题的流程,揭示服装及人体几何模型建立、计算模型与边界条件设定的关键;从着装人体、服装结构、防护服装功能角度回顾了传热问题的国内外研究进展;总结了常用人体热生理模型的特征,介绍了热调节-CFD耦合系统在服装传热性能评价中的应用。现有模拟方法依然存在难以完全还原纺织材料、衣下空间分布、人体热反应等真实特性的问题,建议将动网格、用户自定义函数、数值模型耦合系统等作为深入研究方向,提高仿真评价的准确性。

CHEN Huizhen, DAI Hongqin, PAN Shuwen, et al.

Application of CFD in heat and flow transfer performance evaluation for clothing

[J]. Advanced Textile Technology, 2022, 30(2): 18-26.

DOI:10.19398/j.att.202103026      [本文引用: 1]

To break down the limitations of traditional experimental means and one-dimensional mathematical models, some researchers proposed to simulate the process of heat and flow transfer in human-clothing-environment system based on computational fluid dynamics. Through the calculation of skin temperature, heat transfer coefficient and other parameters, the heat transfer properties of clothing can be evaluated. This paper summarizes the procedure of simulation to solve clothing heat transfer issues, reveals key points on establishing geometries of clothing and human body, calculating models and setting boundary conditions; reviews the progress of heat transfer research at home and abroad from the perspectives of human body, clothing structure, and protective clothing functions; concludes the characteristics of common human thermal physiological models, and introduces how to construct thermal regulation-CFD coupling system in the evaluation. It is found that existing simulation methods are still difficult to completely restore the real characteristics of textile materials, clothing space distribution, and human thermal reaction. Finally, this paper proposes recommendations of conduct in-depth research on dynamic grids, user-defined functions, and numerical model coupling systems so as to enhance the accuracy of simulation evaluation.

LIM J, CHOI H, ROH E K, et al.

Assessment of airflow and microclimate for the running wear jacket with slits using CFD simulation

[J]. Fashion and Textiles, 2015, 2(1): 1.

DOI:10.1186/s40691-014-0025-2      URL     [本文引用: 1]

田苗, 李俊.

基于CFD的闪火环境中消防服传热机制模拟

[J]. 东华大学学报(自然科学版), 2020, 46(5): 740-746.

[本文引用: 1]

TIAN Miao, LI Jun.

Heat transfer mechanism of the firefighter's clothing exposed to the flash fire based on computational fluid dynamics

[J]. Journal of Donghua University (Natural Science), 2020, 46(5): 740-746.

[本文引用: 1]

TIAN M, LI J.

Heat transfer modeling within the microclimate between 3D human body and clothing: effects of ventilation openings and fire intensity

[J]. International Journal of Clothing Science and Technology, 2021, 33(4): 542-561.

DOI:10.1108/IJCST-12-2019-0191      URL     [本文引用: 1]

The purpose of this study is to determine the effect of ventilation openings and fire intensity on heat transfer and fluid flow within the microclimate between 3D human body and clothing.

承奇, 张礼敬, 陶刚, 等.

高架火炬事故状态火焰热辐射危险性分析

[J]. 石油化工高等学校学报, 2009, 22(1): 69-72.

[本文引用: 1]

CHENG Qi, ZHANG Lijing, TAO Gang, et al.

Flame heat radiation hazard analysis of elevated flare under accident condition

[J]. Journal of Petrochemical Universities, 2009, 22(1): 69-72.

[本文引用: 1]

廖宇凡, 陈娟娟, 方正.

油罐火灾中消防员安全施救距离

[J]. 消防科学与技术, 2017, 36(1): 107-110.

[本文引用: 1]

LIAO Yufan, CHEN Juanjuan, FANG Zheng.

Safe distance of fire fighters in oil tank fire extinguishing

[J]. Fire Science and Technology, 2017, 36(1): 107-110.

[本文引用: 1]

马庆春, 贺雅丽.

强风条件下大型储罐火灾的热辐射灾害影响

[J]. 安全与环境学报, 2018, 18(3): 935-940.

[本文引用: 1]

MA Qingchun, HE Yali.

Thermal radiation disasters with the large-sized oil tanks fire usually caused by the strong winds

[J]. Journal of Safety and Environment, 2018, 18(3): 935-940.

[本文引用: 1]

CAMPBELL M J, DENNISON P E, BUTLER B W.

Safe separation distance score: a new metric for evaluating wildland firefighter safety zones using lidar

[J]. International Journal of Geographical Information Science, 2017, 31(7): 1448-1466.

DOI:10.1080/13658816.2016.1270453      URL     [本文引用: 1]

DENNISON P E, FRYER G K, COVA T J.

Identification of firefighter safety zones using lidar

[J]. Environmental Modelling & Software, 2014, 59: 91-97.

[本文引用: 1]

BISGAMBIGLIA P A, ROSSI J L, FRANCESCHINI R, et al.

DIMZAL: a software tool to compute acceptable safety distance

[J]. Open Journal of Forestry, 2017, 7(1): 11-33.

DOI:10.4236/ojf.2017.71002      URL     [本文引用: 1]

LIU X H, TIAN M, SU Y, et al.

Predicting the mechanical strength of fire protective fabrics after thermal aging using machine learning

[J]. AATCC Journal of Research, 2021, 8(2_suppl): 46-50.

[本文引用: 2]

MANDAL S, SONG G W, GHOLAMREZA F.

A novel protocol to characterize the thermal protective performance of fabrics in hot-water exposure

[J]. Journal of Industrial Textiles, 2016, 46(1): 279-291.

DOI:10.1177/1528083715580522      URL     [本文引用: 1]

This study aims to introduce a novel protocol to characterize the thermal protective performance of fabrics used in firefighters’ clothing under hot-water exposure. For this, new and improved test methods were developed to evaluate the performance of a set of fabrics under exposure to hot-water splash and hot-water immersion with compression. The thermal energy transmission through the fabrics tested was thoroughly investigated, and the physical properties that affect the performance of fabrics were statistically identified. It has been found that mainly mass (hot-water) transfer occurs through fabrics in a hot-water splash; whereas, both conductive heat and mass transfer predominate in a hot-water immersion with compression. The compression applied in the exposure of hot-water immersion changes the physical properties of fabrics, thereby reducing fabrics’ performance. The structural configuration and physical properties (e.g., air permeability, thickness) of fabrics are crucial to their heat and mass transfer and therefore to overall fabric performance. This study’s findings may contribute to developing new fabric testing standards, as well as improved thermal protective clothing to provide better occupational safety and health for firefighters.

朱根娣, 朱政康, 张其松, 等.

基于人工神经网络的消防服热防护性能检测数据预测

[J]. 微型电脑应用, 2009, 25(3): 14-16, 61, 4.

[本文引用: 4]

ZHU Gendi, ZHU Zhengkang, ZHANG Qisong, et al.

Test data prediction of thermal protective performance of fire protective clothing based on artificial neural network

[J]. Microcomputer Applications, 2009, 25(3): 14-16, 61, 4.

[本文引用: 4]

UDAYRAJ, TALUKDAR P, DAS A, et al.

Development of correlations and artificial neural network models to predict second-degree burn time for thermal-protective fabrics

[J]. The Journal of the Textile Institute, 2017, 108(2): 260-270.

[本文引用: 4]

MANDAL S, ANNAHEIM S, GREVE J, et al.

Modeling for predicting the thermal protective and thermo-physiological comfort performance of fabrics used in firefighters' clothing

[J]. Textile Research Journal, 2019, 89(14): 2836-2849.

DOI:10.1177/0040517518803779      URL     [本文引用: 4]

\n Standardized test methods are available for measuring the thermal protective as well as thermo-physiological comfort Performance of fabrics used in firefighters' clothing. However, these tests are usually fabric destructive in nature, time consuming, and/or expensive to carry out on a regular basis. Hence, the availability of empirical models could be useful for conveniently predicting the thermal protective and thermo-physiological comfort performances from the fabric properties. The aim of this study is to develop individual models for predicting thermal protective and thermo-physiological comfort performances of fabrics. For this, different single- and multi-layered fabrics that are commercially used to manufacture firefighters' protective clothing were selected, and the fundamental properties of these fabrics (weight, thickness, thermal resistance, air-permeability, evaporative resistance, and water spreading speed) were measured using the standard test methods developed by the International Organization for Standardization (ISO) or the American Association of Textile Chemists and Colorists. The thermal protective performance of these fabrics was measured by the ISO 9151:2016 test method under 80 kW/m\n 2\n flame exposure. The thermo-physiological comfort performance of fabrics was determined by the ISO 18640-1:2018 test method and a statistical model. Thereafter, the key fabric properties affecting the thermal protective and thermo-physiological comfort performances of fabrics were determined statistically. It has been found that thermal and evaporative resistances are the key fabric properties to affect the thermal protective performance, whereas the fabric weight, evaporative resistance, and water spreading speed are the key properties to affect the thermo-physiological comfort performance. By employing these key fabric properties, Multiple Linear Regression and Artificial Neural Network (ANN) models were developed for predicting the thermal protective and thermo-physiological comfort performances. Through a comparison of the predicting performance parameters of these models, it has been found that ANN models can more accurately predict the performances of fabrics. These models can be implemented in the textile industry and academia for effectively and conveniently predicting the thermal protective and thermo-physiological comfort performances only by utilizing the key fabric properties.\n

MÜGE D, YAVUZ S, ENDER YAZGAN B, et al.

Neural network based thermal protective performance predictionof three-layered fabrics for firefighter clothing

[J]. Industria Textila, 2019, 70(1): 57-64.

DOI:10.35530/IT      URL     [本文引用: 2]

BUCKINGHAM E.

On physically similar systems; illustrations of the use of dimensional equations

[J]. Physical Review, 1914, 4(4): 345-376.

DOI:10.1103/PhysRev.4.345      URL     [本文引用: 1]

CHAUDHURI T, ZHAI D Q, SOH Y C, et al.

Random forest based thermal comfort prediction from gender-specific physiological parameters using wearable sensing technology

[J]. Energy and Buildings, 2018, 166: 391-406.

DOI:10.1016/j.enbuild.2018.02.035      URL     [本文引用: 1]

KIM J, ZHOU Y X, SCHIAVON S, et al.

Personal comfort models: predicting individuals' thermal preference using occupant heating and cooling behavior and machine learning

[J]. Building and Environment, 2018, 129: 96-106.

DOI:10.1016/j.buildenv.2017.12.011      URL     [本文引用: 2]

何炎高, 徐定华, 陈瑞林.

纺织材料设计反问题的贝叶斯统计推断方法

[J]. 纺织学报, 2015, 36(1): 23-29.

[本文引用: 1]

HE Yangao, XU Dinghua, CHEN Ruilin.

Bayesian statistical inference method for inverse problems of textile material design

[J]. Journal of Textile Research, 2015, 36(1): 23-29.

[本文引用: 1]

徐定华, 陈远波, 程建新.

低温环境下纺织材料类型设计反问题

[J]. 纺织学报, 2011, 32(9): 24-28.

[本文引用: 1]

本文提出了基于热湿传递稳态模型的低温环境下纺织材料类型设计反问题，即根据人体所处环境温度-湿度值，依据人体服装舒适性指标，已知材料微观结构与厚度，决定材料的类型。根据正则化思想将类型设计反问题的求解归结为一个函数极小化问题。利用非线性常微分方程的正演算法与函数极小化问题的一维Hooke-Jeeves搜索，构造了反问题正则化解的迭代算法。数值模拟验证了算法的有效性和反问题提法的合理性。

XU Dinghua, CHEN Yuanbo, CHENG Jianxin.

Inverse problem of textile material design at low temperature

[J]. Journal of Textile Research, 2011, 32(9): 24-28.

[本文引用: 1]

Based on the model of steady-state heat and moisture transfer through textiles, we put forward an inverse problem of type design for textile materials under low temperature, that is to say, according to the environment&rsquo;s temperature and humidity people live in and the comfort index of clothing, given the textile microcosmic structure and thickness of the material, we determine the type of the material. According to the idea of regularization method, the inverse problem of type design can be formulated into a function minimization problem. Combining the finite difference algorithm for nonlinear ordinary differential equation with direct search method of one-dimensional minimization problems, we construct an iterative algorithm for the regularized solution of the inverse problem. Numerical Simulation shows the effectiveness of the algorithm.

吕婉莹. 两类功能性服装热湿传递数学建模及参数决定反问题[D]. 杭州: 浙江理工大学, 2020:6-26.

[本文引用: 1]

LÜ Wanying. Mathematical modeling of heat and moisture transfer of two kinds of functional clothing and inverse problems of parameter determination[D]. Hangzhou: Zhejiang Sci-Tech University, 2020:6-26.

[本文引用: 1]

王艺融. 两类防护服热湿传递建模与参数决定反问题[D]. 杭州: 浙江理工大学, 2023:19-34.

[本文引用: 1]

WANG Yirong. Modeling of heat and moisture transfer of two kinds of protective clothing and inverse problems of parameter determination[D]. Hangzhou: Zhejiang Sci-Tech University, 2023:19-34.

[本文引用: 1]

王丽燕, 李庆杰, 李雁宙, 等.

基于蒙特卡罗算法的高温作业防护服优化设计

[J]. 大连理工大学学报, 2020, 60(2): 216-220.

[本文引用: 1]

WANG Liyan, LI Qingjie, LI Yanzhou, et al.

Optimal design of high-temperature operation protective clothing based on Monte Carlo algorithm

[J]. Journal of Dalian University of Technology, 2020, 60(2): 216-220.

[本文引用: 1]

卢琳珍. 多层热防护服装的热传递模型及参数最优决定[D]. 杭州: 浙江理工大学, 2018:30-36.

[本文引用: 1]

LU Linzhen. Mathematical model of heat transfer within multilayer thermal protective clothing and corresponding optimal parameter determination[D]. Hangzhou: Zhejiang Sci-Tech University, 2018:30-36.

[本文引用: 1]

ILIFFE C. An inverse predictive model for the design of functional textiles[D]. Newcastle upon Tyne: University of Newcastle Upon Tyne, 2016:150-161.

[本文引用: 1]

ANTUNES L M, BUTLER K T, GRAU-CRESPO R.

Crystal structure generation with autoregressive large language modeling

[J]. Nature Communications, 2024, 15: 10570.

DOI:10.1038/s41467-024-54639-7      [本文引用: 1]

The generation of plausible crystal structures is often the first step in predicting the structure and properties of a material from its chemical composition. However, most current methods for crystal structure prediction are computationally expensive, slowing the pace of innovation. Seeding structure prediction algorithms with quality generated candidates can overcome a major bottleneck. Here, we introduce CrystaLLM, a methodology for the versatile generation of crystal structures, based on the autoregressive large language modeling (LLM) of the Crystallographic Information File (CIF) format. Trained on millions of CIF files, CrystaLLM focuses on modeling crystal structures through text. CrystaLLM can produce plausible crystal structures for a wide range of inorganic compounds unseen in training, as demonstrated by ab initio simulations. Our approach challenges conventional representations of crystals, and demonstrates the potential of LLMs for learning effective models of crystal chemistry, which will lead to accelerated discovery and innovation in materials science.

李秋实, 张凌峰, 吴张阳.

基于人工智能的软体机器人性能与寿命预测方法: 119442808B

[P]. 2025-04-18.

[本文引用: 1]

LI Shiqiu, ZHANG Lingfeng, Wu Zhangyang.

Artificial intelligence-based method for performance and life predlction of soft robots: 11944280813

[P]. 2025-04-18.

[本文引用: 1]

/

〈 〉

京ICP备14006648号　 京公网安备11010502044800号
版权所有 © 2021 《纺织学报》编辑部
地址： 北京市朝阳区延静里中街3号主楼6层《纺织学报》杂志社　邮政编码：100025　
电话：010-65017711,65917740　传真：010-65016539　Email:fangzhixuebao@vip.126.com
本系统由北京玛格泰克科技发展有限公司设计开发