纺织学报, 2026, 47(07): 63-73 doi: 10.13475/j.fzxb.20260405802

第二十八届中国科协年会学术论文·减污降碳共性技术突破专栏·

人工智能赋能纺织产业减污降碳的技术现状及创新路径

艾雨池1, 陆莎,2

1 同济大学 马克思主义学院, 上海 200092

2 同济大学 环境科学与工程学院, 上海 200092

Technology status and innovation pathways of artificial intelligence for synergistic pollution and carbon reduction in textile industry

AI Yuchi1, LU Sha,2

1 College of Marxism, Tongji University, Shanghai 200092, China

2 College of Environmental Science and Engineering, Tongji University, Shanghai 200092, China

通讯作者: 陆莎(1985—),女,副研究员,博士。研究方向为环境管理、绿色金融、固废资源化。E-mail:shalu_sa@outlook.com。

收稿日期: 2026-04-27   修回日期: 2026-05-13  

Received: 2026-04-27   Revised: 2026-05-13  

作者简介 About authors

艾雨池(1997—),女,博士生。主要研究方向为循环经济、环境政策与管理等。

摘要

纺织产业在“双碳”目标约束与全球绿色贸易规则重构的双重压力下,亟需依托人工智能(AI)等先进技术,进一步拓宽减污降碳边界,推动系统性绿色转型。以纺织品全生命周期为分析框架,采用文献综述与案例分析相结合的方法,系统梳理AI赋能纺织产业减污降碳的技术现状,估算各阶段碳减排潜力,以数字产品护照(DPP)为载体分析全生命周期协同的减碳路径。研究结果显示:设计阶段,AI驱动的需求预测可减少大量库存积压,虚拟打样技术有效削减物料消耗与物流碳排放;生产阶段,智能排程与深度学习缺陷检测可降低废品率,染色工艺AI优化的节水节汽效果显著;流通阶段,AI路径规划可降低单位货物碳排放强度;消费阶段,AI推荐与虚拟试衣延长20%的服装使用寿命;回收再生阶段,AI智能分拣大幅提升废旧纺织品单独回收的准确率,AI参数优化提升化学法再生的反应效率和产品纯度。综合各阶段,AI充分赋能下单件标准服装生命周期碳排放可由约15 kg CO2e降至10.9~11.7 kg CO2e,减排潜力达22%~27%。目前,AI已构建覆盖全生命周期的减碳赋能体系,DPP数据协同机制可有效支撑全链条系统性减排,但AI赋能的实际减排效益仍受数据孤岛、算法可解释性不足及跨企业协同机制缺失等因素制约,尚需在技术、标准与产业层面协同推进。

关键词： 人工智能; 纺织产业; 全生命周期; 减污降碳; 数字产品护照

Abstract

Significance In the context of China's 'dual-carbon' targets and the rapid restructuring of global green trade rules, the textile industry is under increasing pressure to advance green transformation. Artificial intelligence (AI) offers potential for pollution and carbon reduction across different stages and scenarios. However, existing studies remain fragmented, mainly focusing on single stages or individual technologies, and lack a full life-cycle analytical framework. This study reviews AI-enabled decarbonization technologies, identifies innovation pathways, and compares applications across design, production, distribution, consumption, and recycling from a textile life-cycle perspective. By linking AI applications with digital product passport (DPP) data, this study clarifies pathways for coordinated value-chain decarbonization and provides theoretical and practical references for the low-carbon transformation of the textile industry.

Progress AI applications for pollution and carbon reduction now extend across the textile life cycle, but their maturity, depth of implementation, and degree of cross-stage integration vary substantially. At the design stage, generative AI and intelligent decision-making systems support a shift from mass production and excess inventory toward demand-driven design and more precise product matching, thereby reducing material waste and overproduction at the source. However, limited technical standardization and restricted data access still constrain wider applications. At the production stage, deep-learning-based visual inspection and intelligent process control have been relatively well developed in quality control, energy-efficiency improvement, and cleaner production, making production the most mature field of AI-enabled decarbonization in textiles. The main barriers are standardized industrial data collection and the integration of heterogeneous data from different production systems. At the distribution stage, AI-based demand forecasting and supply-chain coordination can reduce inventory accumulation and unnecessary production, but full-chain optimization is limited by insufficient data sharing among firms and by commercial barriers. At the consumption stage, AI recommendation systems and virtual try-on technologies can indirectly reduce emissions by improving product-consumer matching and extending garment use, although algorithmic ethics and user privacy require clearer governance. At the recycling stage, intelligent sorting and digital traceability improve fiber identification and quality control, supporting the transition from end-of-life disposal to higher-value recycling. Yet high equipment costs and unstable markets for recycled fibers continue to restrict large-scale deployment. PP provides a data infrastructure for connecting life-cycle information across stages and actors, offering a basis for coordinated decarbonization beyond isolated technological improvements.

Conclusion and Prospect AI has established an initial full life-cycle enabling framework for the textile sector, providing a practical basis for moving from isolated energy-saving measures toward systematic pollution reduction and decarbonization. However, the full mitigation potential of AI remains constrained by algorithmic opacity, limited model generalizability, unaccounted energy consumption from AI computation, and insufficient cross-enterprise data coordination. Future research should focus on four key directions. Firstly, explainable AI should be further applied to textile process optimization to improve engineer intervention while maintaining model accuracy. Secondly, federated learning-based data collaboration mechanisms should be developed to address industry data silos while protecting data ownership and commercial privacy. Thirdly, DPP data standards and pathways for international alignment should be strengthened to support trusted carbon footprint transmission and dynamic accounting across stakeholders. Fourthly, AI-based multi-objective decision-making systems should be developed to jointly optimize carbon emissions, chemical oxygen demand, energy efficiency, and product quality.

Keywords： artificial intelligence; textile industry; full life cycle; pollution and carbon reduction; digital product passport

PDF (10345KB) 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

艾雨池, 陆莎. 人工智能赋能纺织产业减污降碳的技术现状及创新路径[J]. 纺织学报, 2026, 47(07): 63-73 doi:10.13475/j.fzxb.20260405802

AI Yuchi, LU Sha. Technology status and innovation pathways of artificial intelligence for synergistic pollution and carbon reduction in textile industry[J]. Journal of Textile Research, 2026, 47(07): 63-73 doi:10.13475/j.fzxb.20260405802

纺织产业是我国重要的基础性民生产业和国际优势产业,但仍面临资源消耗量大、污染排放较为集中等问题。联合国环境署数据显示,纺织服装业的碳排放量占全球碳排放总量的10%,超过国际航空和海运的总和[1]。我国纺织行业近两年平均碳排放强度降幅超过14%[2],但废旧纺织品仅有约2%被用于工业回收,73%最终被焚烧处置[3],全链条减排潜力远未释放。欧盟《可持续产品生态设计法规》(ESPR)于2024年7月正式生效,将数字产品护照(DPP)作为制度工具,要求整个价值链形成可测量、可验证的量化数据。同时,国际绿色贸易壁垒对出口导向型中国纺织产业的约束日益强化,绿色技术已成为国际竞争中的重要变量。

在此背景下,以人工智能(AI)为核心的新一代信息技术,深刻改变了制造业的生产模式和经济形态,驱动产业升级[1]。研究表明,广泛应用数字技术到2030年可使各行业减少碳排放,受益量约为数字行业自身排放量的10倍[4]。制造业智能化改造后,研发周期缩短约20.7%、生产效率提升约34.8%、碳排放减少约21.2%[5]。此外,纺织产业系统性转型要求覆盖设计、生产、流通、消费、回收再生等多个阶段,进行全流程系统协同[6]。但现有研究普遍缺乏覆盖全生命周期的系统性分析框架,对AI赋能减污降碳的技术传导机制与量化效益评估方法尚不统一。

基于此,本文从纺织品全生命周期视角出发,系统梳理AI赋能纺织产业减污降碳的技术现状与创新路径,以期为纺织产业绿色低碳转型提供理论支撑与实践参考。

1 AI赋能纺织产业减污降碳研究进展

近年来,AI技术在纺织产业的应用已向全生命周期减污降碳延伸,“双碳”目标进一步推动了AI与纺织绿色发展的融合研究[6]。

1.1 设计阶段

设计阶段是源头环节,现有研究主要从3个方面展开。

1)设计与需求预测。以生成对抗网络(GAN)和扩散模型(Diffusion Model)为代表的生成式AI技术已被引入纺织服装图案设计领域,在流行趋势预测、品牌协同设计与消费者个性化定制等场景中取得应用进展[7]。例如:GAN模型可设计出兼具创意和实用价值的新型针织纺织品,优化了流程,节约了设计成本[8]。

2)绿色材料研发。基于智能决策支持系统(IDSS),通过预测分析技术,预估面料特性与成分含量;采用规范分析技术,优化输入预测模型的面料设计参数[9];借助深度生成建模(DGM)技术,将面料开发进程加快100倍以上,显著减少绿色低碳材料的研发周期与成本[10]。

3)智能交互产品设计。多模态感知、强化学习与生成对抗网络等技术被引入纺织产品交互设计,推动产品从传统功能型向智能交互型转变,以实时采集的用户行为数据优化产品设计决策[11]。

设计阶段3类技术路径各有侧重,生成式AI(GAN、扩散模型)输出速度快、创意成本低,但结果可控性弱、对大规模标注数据依赖度高,不适合精准工艺决策;IDSS与DGM在材料性能预测上精度更高、可解释性更强,但需构建专业领域数据库,初期部署成本较高;多模态感知与强化学习在交互产品设计上潜力突出,但工程化门槛高、训练周期长。

1.2 生产阶段

纺织生产阶段是全产业链能耗与污染排放最集中的环节,印染加工过程中产生的CO2排放量占印染行业总量的70%以上[12]。目前,AI在质量检测、工艺控制、生产流程3个方向的应用形成了较为系统的积累。

1)质量检测。卷积神经网络(CNN)是纺织行业中使用最广泛的深度学习(DL)技术(占36.8%)[13],这类模型的计算机视觉系统能将大型生产设施中的面料浪费减少约20%[14]。

2)工艺控制。AI已系统覆盖染料性质预测、智能测配色、工艺参数优化与质量检测4大核心方向[15]:机器学习预测染料最大吸收波长(λmax)的测试集决定系数R2可达0.73~0.99[15];高光谱成像(HIS)与改进循环神经网络(RNN)结合的智能测配色方法,预测误差低至约3%[15];人工神经网络(ANN)结合遗传算法(GA)的染色工艺优化模型R2接近于1[15];基于CNN的算法在AITEX数据集上取得了优异的性能(曲线下面积(AUC)99.25%、准确率97.30%单块检测时间2.66 ms),满足实时性要求,且具有较好的泛化能力[16]。

3)生产流程。企业可以借助AI优化物料流,减少工人移动距离和等待时间,从而提高能效和生产效率[17]。先进智能生产线生产效率相较于常规生产线提升38%,能源利用率提高21%[18]。AI赋能的纺织机械使非计划停机时间减少60%以上,单位能耗降低15%[19]。AI大模型在纺织检测实验室质量管理体系中的应用,预计可提升40%以上的效率[20]。

生产阶段AI技术的减碳效能与数据质量和模型复杂度密切相关。例如CNN在质量检测上精度高、实时性强,但依赖海量标注样本,标注成本高;机器学习(ANN、GA、RF)则在工艺控制中可解释性相对较好,数据需求量适中,适合工艺知识积累较深的传统印染企业,部署门槛低于深度学习。

1.3 流通阶段

流通阶段的供应链协同效率与物流碳排放水平,直接影响纺织产业全链条的减碳成效。

1)库存把控。AI算法(如RF、DT、ANN)通过分析历史销售数据、季节趋势和消费者情绪,更准确地预测产品需求[21],有效抑制因“预测性浪费”而导致的过度生产,从而避免大量未售出产品最终被填埋或焚烧[21]。

2)退货管理。使用三维虚拟试穿后,退货率降低了27%[22]。同时,消费者若使用手机摄像头进行自助量体,借助AI选择合适产品[23],可从源头减少因退货产生的运输碳足迹和包装垃圾。

此阶段AI技术的减碳效能依赖于供应链数据的开放程度。需求预测算法(RF、DT、ANN)部署成本相对可控,核心约束在于历史销售数据的质量与上下游相关方的共享意愿,数据壁垒问题突出;三维虚拟试穿技术硬件与建模成本较高,短期内主要适用于高客单价品类和头部平台,但其对退货率的压降在减少逆向物流碳排放方面发挥了独特优势。

1.4 消费阶段

消费阶段对纺织业碳排放的影响日益凸显[24],现有研究主要从物理耐久性(生产端驱动)和情感耐久性(消费端驱动)2个维度切入。

1)物理耐久性。AI为消费者提供更精确的数据与个性化服装调整,减少因不合身而被弃置的可能性[21];基于深度学习的智能纺织品传感器可实时监测用户的生理和行为数据,自修复功能(如自修复涂层)延长了功能性服装的使用寿命[25]。

2)情感耐久性。AI通过个性化推荐和交互体验,增强消费者与产品之间的情感联系,从而提高用户对产品的保留意愿,避免过早淘汰。下一代AI,特别是受大脑启发的脉冲神经网络和神经形态计算,有望成为电子纺织品领域“嵌入式智能”的新驱动力[26]。这些AI应用构建了产品与用户的交互范式,形成可感知、可响应的情感依附机制[21]。

比较2种类型,物理耐久性依赖传感器硬件与材料研发的协同,技术链条长、落地成本高,但减碳效果可量化;情感耐久性以软件推荐算法为核心,边际成本低、易规模化,但减碳效果难归因,且高度依赖用户行为数据,数据合规成本存在争议,算法推荐的“信息茧房”效应也可能导致过度消费反而增加碳排放。

1.5 回收再生阶段

回收再生阶段是纺织品全生命周期中技术难度最大、AI参与工作较多的过程。

1)智能分拣技术。结合深度学习的近红外(NIR)光谱、多光谱与成像光谱技术,可实现混纺织物高精度识别与分离[27]。其中,CNN方法在多数色系分类中表现最优,平均准确率可达86.1%[28];NIR光谱和CNN系统在识别纯纤维方面能达到96%~100%的准确率[29],有效避免人工检测的主观性和低效率[30];红外光谱分拣应用及再生纤维定性鉴别等技术为建立废旧纺织品循环经济监督检验体系提供了重要支撑[31]。

2)再生利用技术。在再生工艺参数优化方面,化学法再生是高值化利用的核心路径[32],AI的引入可对醇解反应中多参数组合进行智能优化,提升反应效率和产品纯度;在再生产品质量评估方面,AI辅助的绿色溶剂筛选与高效催化剂开发是突破多品类纤维分类回收技术壁垒的核心方向。

3)回收再生体系优化。AI驱动的信息化协同机制通过对回收网点布局、回收量预测与物流路径的数据驱动优化,有效提升回收体系的运营效率与经济可行性[33];以数字化逆向追溯为核心驱动机制,可推动消费品牌加大再生原料使用比例[34];再生原料的替换率和质量直接影响再生循环的环境效益[35],AI评估系统可提升环境效益计算精度。

回收再生阶段AI技术应用的核心差异体现在识别精度、处理速度与设备成本3个维度。NIR结合深度学习在纤维成分识别中准确率最高,但光谱设备价格昂贵、维护要求高,且对深色和混纺织物的识别稳定性仍有待提升;化学法再生的AI参数优化应用潜力大,但工程化成本高,对催化剂和溶剂体系的专业要求制约了中小回收企业的可及性;回收网络优化的算法门槛不高,主要障碍在于回收量预测所需的数据来源分散,以及各区域运营主体的协同意愿不足。

深度融合数字技术正是推动纺织产业从多维度实现绿色创新的核心驱动[36],数字化技术、智能制造和环保染色技术等新质生产力要素的综合作用,能够助力行业实现从传统制造向高附加值、智能化、绿色化现代产业的跨越[37]。综观现有研究,仍存在3方面不足之处。一是缺乏全生命周期系统性分析。从研究范式看,工程技术类研究偏重局部性能优化,环境管理类研究侧重末端效应评估;从产业结构看,纺织价值链主体高度分散,跨阶段数据的采集与贯通在现实中面临较高的协调成本;从数据标准看,不同阶段的碳排放核算边界与功能单位定义不统一,导致跨阶段效益比较缺乏共同基准。二是数据贯通与系统协同机制存在瓶颈。在技术层面,行业数据格式与接口标准高度碎片化,各类设备、平台与管理系统之间的数据互通成本高昂,“数据孤岛”问题突出;在利益层面,核心工艺数据与客户数据的权属争议缺乏明确的法律界定和市场化解决机制,商业壁垒难以依靠单一技术手段突破;在能力层面,中小纺织企业数字化基础薄弱,数据采集与处理能力的差距使规模化协同在短期内难以实现;三是AI技术自身存在局限性。当前研究普遍聚焦于AI的技术潜力,而对其在纺织应用场景中的内在局限性关注不足。其一,算法“黑箱”问题在可解释性要求较高的工艺优化场景中构成实质性障碍,目前可解释AI(XAI)框架的引入是较为可行的应对方向,但相关研究在纺织领域较少。其二,模型泛化能力受限于训练数据的代表性,纺织生产中设备型号、原料批次、气候环境等变量多样,特定企业环境中训练的模型往往难以跨厂迁移,制约了规模化应用。其三,AI系统自身的训练与推理过程存在不可忽视的算力能耗,目前暂未系统测算并将这一“AI碳成本”纳入全生命周期的净减排效益核算。

上述3方面不足表明,推动AI赋能纺织产业深度减碳,不能仅依赖单点技术突破,还需在数据标准建设、跨主体协同机制和AI模型可信度提升3个层面协同推进。

2 全生命周期减污降碳的路径

依据已有研究数据,对AI赋能下纺织品全生命周期各阶段碳减排潜力进行测算。设基准年单位产品(以1件标准棉质服装为例,约重0.3 kg)生命周期碳排放为15 kg CO2e(含原料种植/化纤生产约5.5 kg、纺纱织造约1.5 kg、印染整理约4.0 kg、运输流通约1.0 kg、消费使用约1.5 kg、废弃处置约1.5 kg),各阶段AI介入后减排潜力估算如下:

过剩生产率降低20%~30%[38],折算碳减排1.10~1.65 kg CO2e/件;印染碳排放可降低15%~20%,0.6~0.8 kg CO2e/件;坯布废品率降低约20%[14],按纺纱织造阶段(1.5 kg)折算碳减排约0.3 kg CO2e/件;智能调度可使运输碳排放降低10%~15%[10],折算0.1~0.15 kg CO2e/件;服装穿用次数每增加1倍,碳排放减少44%[6],减排约0.66 kg CO2e/件;废旧纺织品单独回收碳排放(221.31 kg/t)较混入回收碳排放(343.97 kg/t)下降约35%[39],可减排0.53 kg CO2 e/件。综合各阶段,在AI充分赋能的情景下,单件服装生命周期碳排放由约15 kg CO2e降至10.9~11.7 kg CO2e,全链条减排潜力达22%~27%。

基于此,提出AI赋能纺织产业全链条减污降碳的具体路径,如图1所示。

图1

新窗口打开| 下载原图ZIP| 生成PPT

图1   AI赋能纺织全生命周期减污降碳技术路径

Fig.1   AI-Enabled technical pathways for pollution reduction and carbon mitigation across textile life cycle


2.1 源头约束与需求匹配设计阶段

设计阶段是纺织品全生命周期减污降碳的起点。产品全生命周期中约80%的资源环境影响取决于设计阶段的决策[40],AI在设计阶段的应用主要通过3大路径发挥作用。

1)消费数据驱动的需求预测与“小单快反”模式。传统“批量生产、集中销售、尾货处理”的线性模式造成大量库存积压与资源浪费。AI驱动的需求预测技术通过整合历史销售数据、社交媒体趋势、搜索热词及实时消费者信号,显著提升预测准确率,为“小批量、快测试、快反应”的生产模式提供数据基础。以SHEIN为代表的快时尚平台通过机器学习模型识别潜在流行趋势,以极小批量(通常仅召集50~100件)进行试产,依据销售反馈决定是否追加。该模式使库存周转率大幅提升,库存压力降低20%~30%[38],有效减少因滞销库存被填埋或焚烧而产生的碳排放。

2)数字仿真设计与虚拟打样技术。传统实物打样每轮打样均涉及材料消耗、运输碳排放与生产能耗。数字仿真与虚拟打样技术以三维建模、物理仿真引擎与机器学习算法,从源头大幅削减实物样品的物料消耗[10]。例如:耐克(Nike)通过将AI驱动的虚拟打样系统整合进产品开发流程,降低样品阶段的原材料消耗与物流碳排放;Style3D等国内平台的AI多模态生成模型满足基础设计需求外,还能精准捕捉市场趋势,与“小单快反”模式形成协同,推动设计端与流通端的跨阶段减碳效应。

3)数据驱动的再生材料选择优化。材料选择是影响碳排放的关键变量之一。《2024年中国趋势面料报告》显示,59%的受访者表示在选购服装时,会经常考虑面料的环保属性[41]。AI赋能材料选择的核心在于通过机器学习模型建立材料物理性能、加工适配性与碳足迹之间的多维关联[36]。例如:Adidas将碳足迹信息从末端核算提前嵌入设计决策,截至2024年产品中再生聚酯纤维的使用率高达99%[42]。

2.2 过程优化与清洁生产阶段

AI在生产阶段的减污降碳作用机制可归纳为3个层次:生产排程优化减少无效能耗、染整工艺智能控制降低化学品与能源消耗、深度学习缺陷检测减少面料废品率。

1)生产排程优化与设备能效管控。AI驱动的智能排程系统通过对生产订单、设备状态、能耗数据与交期约束的多目标优化,动态调整生产计划,最大化设备利用率,降低单位产品能耗;设备能效管控系统可对纺纱、织造、印染等核心设备的运行状态进行实时监测,识别异常能耗节点,提前预警设备故障,减少非计划停机造成的能源浪费[19]。例如:申洲国际通过自主研发的CPS生产协同系统实现生产计划的动态优化,生产效率提升30%,订单交付周期缩短25%[43]。其中,安徽智能制造项目引入全自动吊挂生产线与AI视觉质检,预计生产效率提高40%[43],能耗降低20%[43]。

2)染整工艺智能控制与减排。其一是通过机器学习预测染色过程中的关键工艺参数,减少因参数偏差导致的返修、返染与废水排放;其二是通过智能测配色技术降低配方试错次数,减少染料与化学品的过量使用[15]。例如:鲁泰纺织AI辅助的染色工艺优化系统可实现染色合格率95%以上,在万吨级染色产能下节约用水27%,节约蒸汽19.4%,节约用电12.5%,减少废水排放26.7%,推动能效与环境效益的协同提升[44]。

3)深度学习织物缺陷检测与减废。基于CNN、YOLO等深度学习模型的计算机视觉系统,能够实时高准确度地识别织物表面各类缺陷,并及时反馈至生产系统,为工艺调整提供数据依据[45]。中国电信的星辰视觉大模型AI验布机可识别20余类常见缺陷,检测准确度达到0.06 mm,布匹缺陷检出率达90%[46];番禺智能验布机纺织品瑕疵检测准确率达97%[47]。

2.3 供应链协同与系统减损流通阶段

AI在流通阶段可通过信息的实时整合与协同优化,系统性消除供应链各环节的“摩擦性浪费”,实现从订单到交付全链条的减损与降碳。

1)射频识别(RFID)与AI协同的智能库存调度。通过对门店库存的实时感知与跨门店、跨仓储节点的智能调拨,可消除传统库存管理的信息滞后问题[48]。例如:Inditex在全球门店部署RFID标签,通过AI分析门店销售速度、区域需求差异与季节性趋势,动态调整补货计划与跨区调拨策略,库存盘点准确率提升至98%以上,补货速度提升30%。

2)运输路径优化算法与碳减排。AI驱动的路径优化算法对配送需求、路网条件、车辆载重与时间窗口等多约束条件的动态求解,识别最优运输方案,减少行驶里程并提升车辆满载率,直接降低单位货物运输的碳排放强度[10]。例如:京东物流通过部署AI驱动的智能路由规划系统,2024年实现减碳超35万t[49]。对纺织行业而言,AI驱动的物流优化支撑了“小单快反”的生产模式,形成设计端到流通端的跨阶段协同减碳效应[36]。

3)智能包装优化。AI参与的智能包装优化系统可以通过分析商品尺寸、质量与组合方式,自动匹配最优包装规格,减少过度包装;基于数字协同平台的供应链信息共享机制,能打破品牌商、供应商、物流商与零售商之间的数据壁垒,减少因信息不对称导致的重复运输、返仓处理与过量备货等系统性损耗[33]。2025年公布的《快递暂行条例》修订内容,明确“包装绿色化、减量化、可循环”的转型路径[50]。京东自主研发的X系列纸箱单个原材料用量降低5%~25%,年度减少碳排放量1.2万t[49];菜鸟结合AI系统测算商品体积,生成最优纸箱型号、摆放方案及装箱顺序,精准减少填充物使用。

2.4 需求引导与行为优化机制消费阶段

生产阶段的减碳作用于物质流的转化效率,而消费阶段的减碳则作用于需求流的引导与行为模式的优化。

1)用户行为数据分析与精准推荐。AI驱动的个性化推荐系统通过深度学习用户的浏览习惯、购买历史与风格倾向等,向消费者推送高匹配产品,有助于延长实际使用周期,提升产品全生命周期的碳效率[51]。例如:淘宝平台通过深度神经网络构建“用户、商品、场景”三维匹配模型,结合实时行为信号动态调整推荐策略,使消费者以更低的搜索成本发现产品。阿里巴巴2024年ESG报告披露,2024财年集团通过带动消费者购买低碳友好商品和助力循环经济发展,共计减排1 010万t[52]。

2)虚拟试衣技术与逆向物流控制。三维虚拟试衣技术通过AI驱动的体型扫描、参数化建模与虚拟试穿模拟,在购买前提供高度仿真的穿着效果预览,降低因信息不对称带来的产品失配风险[10]。Zalando的AI尺码推荐系统使相关产品的退货率降低10%以上。

3)AI辅助环境信息披露。消费者绿色消费意愿与实际绿色消费行为之间的落差部分源于难以便捷获取产品真实环境信息[53]。AI辅助的环境信息披露机制通过将产品碳足迹、材料来源与生产工艺的绿色属性以数字化、可视化的方式呈现,降低绿色消费的信息获取成本,激活消费者的绿色购买意愿[54]。欧盟生态标签(The EU Eco-label)关注纺织品耐色牢度和保型性标准、水资源使用、限制性危险物质以及在生产过程中向水和空气中的减排信息等方面,其逻辑与DPP制度在逻辑上高度契合,代表了消费阶段环境信息透明化的重要方向[55]。

2.5 资源循环与再生优化机制回收再生阶段

废旧纺织品成分复杂、混纺比例高,传统回收体系严重制约了再生纤维的品质与规模[27]。AI在回收再生阶段通过智能分拣、数字追溯与回收网络的优化实现减污降碳。

1)NIR与深度学习融合的纤维分拣技术。NIR技术通过检测纤维对近红外光的吸收特征,快速获取材料的化学组成信息,再由DL对光谱特征进行高精度解析,实现对棉、涤纶、锦纶等不同纤维成分的精准识别与分类。Tomra将高精度NIR、可见光(VIS)光谱传感技术与深度学习算法集成于全自动分拣设备,实现对棉、涤纶及混纺材料的高精度区分。分拣精度的提升直接影响再生纤维的品质,而高品质的再生纤维正是推动废旧纺织品从末端处置向高值循环转型的技术起点。

2)再生资源数字追溯与高值化利用再生纤维的追溯认证体系不健全、质量参差不齐,制约了再生纤维的应用[56]。例如Renewcell纺织公司将废旧棉纺织品通过化学法溶解再生为高纯度溶解浆(Circulose),再加工成再生纤维素纤维,供应至时尚品牌的产品线。而AI支撑的数字追溯体系可对这一过程各环节数据的全程记录与上链存证,为再生原料提供可查验的质量档案[34]。

3)AI驱动的回收网络优化。AI驱动的回收网络优化系统可以通过对各区域废旧纺织品产生量的预测、回收网点布局的动态调整与收运路径的优化,提升回收体系的整体运营效率与经济可行性[33]。例如:浙江联运环境建成的全国首个第四代绿色数智分拣中心融合了AI识别、云镜大模型、数字孪生等前沿技术,分拣准确率超过99%,分拣效率是人工分拣的3倍[57],推动废旧纺织品回收利用从分散低效走向体系化、规模化和高值化发展。

2.6 全生命周期协同机制数字产品护照

数字产品护照(DPP)为每件产品配置贯通全生命周期的数字身份档案,将材料成分、生产工艺、碳足迹、维修记录与回收处置信息整合于统一数据载体,实现全流程数据贯通[55]。DPP不仅是欧盟绿色贸易规则的重要组成部分,更是AI赋能纺织全生命周期协同减碳的制度与技术抓手。

1)与纺织印染工艺的技术衔接。DPP在生产阶段可将印染工艺参数与环境排放数据进行标准化数字记录,形成可跨主体传递的工艺环境档案。技术路径上,印染工序中AI优化系统的输入参数与输出结果可通过IoT接口实时写入DPP数据层;区块链技术对上述数据进行存证;AI辅助的生命周期评估(LCA)工具基于DPP中的多维数据,自动化地生成实时动态的产品碳足迹报告,替代传统人工LCA的高成本与低时效[35]。当产品碳足迹数据以标准化方式向供应链下游开放时,碳减排的压力与激励机制将从终端品牌向上游供应商延伸,形成贯通全供应链的碳约束传导效应。

2)基于产品数据的纺织回收工艺发展。DPP可为废弃纺织品智能分拣系统提供先验材料成分信息,提升回收工艺效率与再生纤维品质。产品设计阶段写入DPP的纤维成分、染料类型与整理剂信息,可在回收端通过扫描产品标识直接读取,辅助NIR光谱分拣系统预先设定识别模型参数,减少光谱特征的误判概率;化学法再生工艺可根据DPP中的聚合物牌号与染色信息,预设最优的反应温度、催化剂浓度与溶剂配比,从而提升反应效率与产品纯度。再生原料经AI辅助的质量检测后,检测结果同步上链至DPP,为再生材料提供可追溯的质量认证。2026年3月,国家先进功能纤维创新中心与国际合作伙伴Aware平台联合发布首版再生涤纶全链路数字化产品护照,实现从订单、原料到成品的全流程数据透明追溯,为产品贴上“绿色身份证”,标志着DPP在我国纺织行业的落地应用取得实质性突破。

3)全流程数据贯通与生命周期信息集成。DPP技术实现依赖于跨阶段、跨主体的数据采集与整合。在技术路径上,DPP通过集成标识、物联网、区块链、可信数据空间等,构建覆盖数据采集、标识、存证与核验的全链路闭环;AI在该系统中可承担数据筛选、信息标准化与跨系统互操作的技术支撑角色,将来源各异、格式不一的多元数据转化为可比较、可分析的结构化信息[35]。

3 结束语

我国纺织产业在设计、生产、流通、消费与回收再生各环节均蕴含着巨大的减污降碳潜力,人工智能(AI)已初步形成覆盖纺织品全生命周期的技术赋能体系。在设计阶段,AI驱动的需求预测与虚拟打样从源头削减了物料浪费与“预测性过剩”;在生产环节,智能排程、染整工艺控制与深度学习缺陷检测显著降低了能耗、化学品消耗与废料率;在流通阶段,射频识别(RFID)智能调度与运输路径优化系统性消除了供应链中的“摩擦性浪费”;在消费环节,AI通过精准推荐与虚拟试衣驱动了生产端及消费端根源性减碳;在回收再生阶段,近红外NIR光谱与深度学习融合的智能分拣技术结合数字追溯体系,正在推动废旧纺织品从“末端处置”向“高值循环”转型。以数字产品护照(DPP)为载体的全生命周期数据贯通机制,则为AI赋能全链条协同减碳提供了转型路径。

未来AI赋能纺织减污降碳的研究需在以下4个方向实现突破。一是可解释AI(XAI)在纺织工艺优化中的应用,重点探索如何将沙谱利值(SHAP值)、注意力机制等可解释性工具加入染整工艺模型,在保持预测准确度的同时提升工程师的可干预性。二是探索基于联邦学习的隐私保护型跨企业数据协同机制,在不共享原始数据的前提下实现跨企业、跨阶段的联建,从而打破数据孤岛。三是DPP数据标准与全球互认机制研究,实现跨主体数据可信传递与碳足迹动态核算的技术规范。四是多目标协同优化的AI统筹决策系统,探索多目标强化学习(RL)与帕累托最优在纺织工艺优化中的应用,建立兼顾碳排放最小化、化学需氧量排放最低化、能源效率最大化与产品质量最优化等多重目标的AI统筹决策系统。综上,AI赋能纺织产业减污降碳已进入规模化应用的关键期,需在不同方向实现交叉突破,才能进一步推动我国纺织产业真正迈向全生命周期减污降碳。

参考文献

生态中国网.

90%纺织企业设定气候目标,从纤维到成衣碳足迹核算待突破

[EB/OL]. (2025-06-27)[2026-04-24]. https://www.eco.gov.cn/news_info/60641.html.

URL     [本文引用: 2]

Eco China.

90% of textile enterprises set climate goals, carbon footprint accounting from fiber to garment awaits breakthrough

[EB/OL]. (2025-06-27)[2026-04-24]. https://www.eco.gov.cn/news_info/60641.html.

URL     [本文引用: 2]

中国质量新闻网.

我国纺织行业单位产值能耗近20年下降超65% 再生纤维年使用量突破300万吨

[EB/OL]. (2025-09-11)[2026-04-24]. https://www.cqn.com.cn/zgzlb/content/2025-09/10/content_9122730.htm.

URL     [本文引用: 1]

China Quality News Network.

Energy consumption per unit output value of China's textile industry has dropped by more than 65% in the past two decades, annual use of recycled fiber exceeds 3 million tons

[EB/OL]. (2025-09-11)[2026-04-24]. https://www.cqn.com.cn/zgzlb/content/2025-09/10/content_9122730.htm.

URL     [本文引用: 1]

中国环保协会.

废旧纺织品回收量持续增长背后:纺织行业迎来线性经济转向循环经济变革

[EB/OL]. (2025-09-04)[2026-04-24]. http://www.zhb.org.cn/gyhb/gyhb_3/2025-09-04/23739.html.

URL     [本文引用: 1]

China Environmental Protection Association.

Behind the continuous growth of waste textile recycling: the textile industry ushers in a transformation from linear economy to circular economy

[EB/OL]. (2025-09-04)[2026-04-24]. http://www.zhb.org.cn/gyhb/gyhb_3/2025-09-04/23739.html.

URL     [本文引用: 1]

中国新闻网.

GeSI: 到2030年,ICT技术助力全球二氧化碳当量排放减少20%

[EB/OL]. (2022-04-27)[2026-04-24]. https://www.chinanews.com.cn/cj/2022/04-27/9741290.shtml.

URL     [本文引用: 1]

China News Service.

GeSI:ICT technologies will help reduce global CO2 equivalent emissions by 20% by 2030

[EB/OL]. (2022-04-27)[2026-04-24]. https://www.chinanews.com.cn/cj/2022/04-27/9741290.shtml.

URL     [本文引用: 1]

中华人民共和国中央人民政府.

“智”造有“数” 企业扩“路”——工业企业加力布局智能制造

[EB/OL]. (2023-07-11)[2026-04-24]. https://www.gov.cn/yaowen/liebiao/202307/content_6891229.htm.

URL     [本文引用: 1]

The State Council of the People's Republic of China.

Intelligent manufacturing with data drives enterprises' expansion-industrial enterprises accelerate deployment of smart manufacturing

[EB/OL]. (2023-07-11)[2026-04-24]. https://www.gov.cn/yaowen/liebiao/202307/content_6891229.htm.

URL     [本文引用: 1]

杜欢政, 刘建成, 陆莎.

双碳目标下纺织产业的绿色创新与发展

[J]. 纺织学报, 2022, 43(9): 120-128.

[本文引用: 3]

DU Huanzheng, LIU Jiancheng, LU Sha.

Green innovation and development of textile industry under dual carbon goals

[J]. Journal of Textile Research, 2022, 43(9): 120-128.

[本文引用: 3]

李鑫.

人工智能技术在纺织服装图案设计领域的应用

[J]. 纺织导报, 2023(6): 110-112.

[本文引用: 1]

LI Xin.

Application of AI technology in textile and apparel pattern design

[J]. China Textile Leader, 2023(6): 110-112.

[本文引用: 1]

WU X P, LI L.

An application of generative AI for knitted textile design in fashion

[J]. The Design Journal, 2024, 27(2): 270-290.

DOI:10.1080/14606925.2024.2303236      URL     [本文引用: 1]

RIBEIRO R, PILASTRI A, MOURA C, et al.

A data-driven intelligent decision support system that combines predictive and prescriptive analytics for the design of new textile fabrics

[J]. Neural Computing and Applications, 2023, 35(23): 17375-17395.

DOI:10.1007/s00521-023-08596-9      [本文引用: 1]

佟欢, 刘洋洋.

人工智能技术在减少纺织服装行业碳排放中的发展与应用

[J]. 印染, 2024, 50(6): 89-95.

[本文引用: 5]

TONG Huan, LIU Yangyang.

Development and application of artificial intelligence technology in reducing carbon emissions in the textile and apparel industry

[J]. China Dyeing and Finishing, 2024, 50(6): 89-95.

[本文引用: 5]

谢嘉欣, 朱诗源.

人工智能驱动的纺织产品交互创新机制与设计模式研究

[J]. 染整技术, 2025, 47(10): 66-68.

[本文引用: 1]

XIE Jiaxin, ZHU Shiyuan.

Research on the interactive innovation mechanism and design patterns of textile products driven by artificial intelligence

[J]. Textile Dyeing and Finishing Journal, 2025, 47(10): 66-68.

[本文引用: 1]

杨会玲, 杨爱民, 骆睿.

纺织印染行业的碳排放情况和碳减排技术

[J]. 染整技术, 2021, 43(11): 1-3.

[本文引用: 1]

YANG Huiling, YANG Aimin, LUO Rui.

Carbon emission situation and carbon emission reduction technology in textile printing and dyeing industry

[J]. Textile Dyeing and Finishing Journal, 2021, 43(11): 1-3.

[本文引用: 1]

MAJUMDAR A, BHATTACHARYYA R, YADAV V S.

Deep learning applications in textile industry: a systematic review of current status and delineating future research agenda

[J]. Archives of Computational Methods in Engineering, 2026, 33(2): 2205-2227.

DOI:10.1007/s11831-025-10366-w      [本文引用: 1]

OZEK A, SECKIN M, DEMIRCIOGLU P, et al.

Artificial intelligence driving innovation in textile defect detection

[J]. Textiles, 2025, 5(2): 12.

DOI:10.3390/textiles5020012      URL     [本文引用: 2]

The cornerstone of textile manufacturing lies in quality control, with the early detection of defects being crucial to ensuring product quality and sustaining a competitive edge. Traditional inspection methods, which predominantly depend on manual processes, are limited by human error and scalability challenges. Recent advancements in artificial intelligence (AI)—encompassing computer vision, image processing, and machine learning—have transformed defect detection, delivering improved accuracy, speed, and reliability. This article critically examines the evolution of defect detection methods in the textile industry, transitioning from traditional manual inspections to AI-driven automated systems. It delves into the types of defects occurring at various production stages, assesses the strengths and weaknesses of conventional and automated approaches, and underscores the pivotal role of deep learning models, especially Convolutional Neural Networks (CNNs), in achieving high precision in defect identification. Additionally, the integration of cutting-edge technologies, such as high-resolution cameras and real-time monitoring systems, into quality control processes is explored, highlighting their contributions to sustainability and cost-effectiveness. By addressing the challenges and opportunities these advancements present, this study serves as a comprehensive resource for researchers and industry professionals seeking to harness AI in optimizing textile production and quality assurance amidst the ongoing digital transformation.

周青青, 常硕, 毛志平, 等.

人工智能在纺织印染行业中的应用研究进展

[J]. 纺织学报, 2025, 46(12): 260-268.

[本文引用: 5]

ZHOU Qingqing, CHANG Shuo, MAO Zhiping, et al.

Research progress in applications of artificial intelligence in dyeing and finishing industry

[J]. Journal of Textile Research, 2025, 46(12): 260-268.

[本文引用: 5]

SERVI M, MAGHERINI R, BUONAMICI F, et al.

Integration of artificial intelligence and augmented reality for assisted detection of textile defects

[J]. Journal of Engineered Fibers and Fabrics, 2024, 19: 15589250231206502.

[本文引用: 1]

PERVEZ M N, MONDAL M I H, CAI Y, et al. Textile waste management and environmental concerns[M]//Fundamentals of natural fibres and textiles. Cambridge: Woodhead Publishing, 2021: 719-739.

[本文引用: 1]

殷强.

人工智能在纺织行业生产领域的应用

[J]. 纺织导报, 2024(5): 30-32.

[本文引用: 1]

YIN Qiang.

AI applications in the textile industry production

[J]. China Textile Leader, 2024(5): 30-32.

[本文引用: 1]

李冰, 徐利云.

人工智能驱动下纺织机械自动化的技术创新与发展趋势研究

[J]. 染整技术, 2025, 47(12): 149-151.

[本文引用: 2]

LI Bing, XU Liyun.

Research on technological innovation and development trends of textile machinery automation driven by artificial intelligence

[J]. Textile Dyeing and Finishing Journal, 2025, 47(12): 149-151.

[本文引用: 2]

陈嘉勋.

AI在纺织检测实验室质量管理体系中的应用

[J]. 针织工业, 2026(1): 85-89.

[本文引用: 1]

CHEN Jiaxun.

Application of AI in the quality management system of textile testing laboratories

[J]. Knitting Industries, 2026(1): 85-89.

[本文引用: 1]

DONG W T, LIANG J Q, SUH S.

Effectiveness of AI technologies in reducing textile waste in the fashion industry

[J]. Textile Research Journal, 2026, 96(3/4): 428-451.

DOI:10.1177/00405175251357582      URL     [本文引用: 4]

Currently, artificial intelligence (AI) technology offers opportunities to address serious challenges in waste management in the fashion industry. This study systematically reviewed and analyzed literature on AI applications in textile waste management from 2014 to 2024. We aimed to review the intervention effects of AI technologies on textile waste across stages of the fashion industry lifecycle and explore AI’s role in promoting circular supply chains (CSCs). The results show that AI plays a prominent role in four key areas: Enhanced intelligent analysis of market dynamics, optimizing consumer experience-oriented durability design, collaboratively optimizing production processes and inventory management, and advancement of intelligent waste management. Convolutional neural networks are the most widely used AI technology due to their strength in image recognition. However, AI technologies also face limitations such as high data requirements. Future research should attempt to promote improvements in policies, enterprise, and technologies to unleash greater potential for AI in CSCs.

HWANGBO H, KIM E H, LEE S H, et al.

Effects of 3D virtual 'try-on' on online sales and customers' purchasing experiences

[J]. IEEE Access, 2020, 8: 189479-189489.

DOI:10.1109/Access.6287639      URL     [本文引用: 1]

KARADAYI-USTA S.

Role of artificial intelligence and augmented reality in fashion industry from consumer perspective: sustainability through waste and return mitigation

[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108114.

DOI:10.1016/j.engappai.2024.108114      URL     [本文引用: 1]

杜欢政, 宋淑苇, 毛志强, 等.

绿色消费驱动下纺织产业绿色转型机制研究

[J/OL]. 棉纺织技术,1-10[2026-04-23]. https://doi.org/10.26967/j.issn1000-7415.202601006.

URL     [本文引用: 1]

DU Huanzheng, SONG Shuwei, MAO Zhiqiang, et al.

Research on green transformation mechanism of textile industry driven by green consumption

[J/OL]. Cotton Textile Technology, 1-10[2026-04-23]. https://doi.org/10.26967/j.issn1000-7415.202601006.

URL     [本文引用: 1]

ZHAO P F, SONG Y L, HU Z P, et al.

Artificial intelligence enabled biodegradable all-textile sensor for smart monitoring and recognition

[J]. Nano Energy, 2024, 130: 110118.

DOI:10.1016/j.nanoen.2024.110118      URL     [本文引用: 1]

CLEARY F, SRISA-AN W, HENSHALL D C, et al.

Emerging AI technologies inspiring the next generation of e-textiles

[J]. IEEE Access, 2023, 11: 56494-56508.

DOI:10.1109/ACCESS.2023.3282184      URL     [本文引用: 1]

何俊, 王斌昊, 王佳馨, 等.

废旧纺织品高效分拣、解聚与高值再生技术进展

[J/OL]. 科学通报,1-25[2026-04-23].

URL     [本文引用: 2]

HE Jun, WANG Binhao, WANG Jiaxin, et al.

Progress in efficient sorting, depolymerization and high-value regeneration technologies for waste textiles

[J/OL]. Chinese Science Bulletin, 1-25[2026-04-23].

URL     [本文引用: 2]

FURFERI R.

Advancing circular economy practices using AI-powered colour classification of textile fabrics: overview and roadmap

[J]. Textiles, 2025, 5(4): 53.

DOI:10.3390/textiles5040053      URL     [本文引用: 1]

Classification is a crucial task for reintroducing end-of-life fabrics as raw materials in a circular process, thus reducing reliance on dyeing processes. In this context, this review explores the evolution of automated and semi-automated colour classification methods, emphasizing the transition from deterministic techniques to advanced methods, with a focus on machine learning, deep learning, and particularly Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). These technologies show potential for improving accuracy and efficiency. The results highlight the need for enriched datasets, deeper AI integration into industrial processes, and alignment with circular economy objectives to enhance sustainability without compromising industrial performance. Tested against a case study, the different architectures confirmed the state-of-the-art statements demonstrating that they are effective in classification, with better performance reached by CNN-based methods, which outperforms other methods in most colour families, with an average accuracy of 86.1%, indicating its adaptability for this task. The adoption of the proposed AI-based colour-classification roadmap could be effective in reducing dyeing operations, lower costs, and improve sorting efficiency for textile SMEs.

FAGHIH E, SAKI Z, MOORE M.

A systematic literature review: AI-enabled textile waste sorting

[J]. Sustainability, 2025, 17(10): 4264.

DOI:10.3390/su17104264      URL     [本文引用: 1]

李胜臻, 王洋, 吴启帆.

基于专利视角的人工智能技术在纺织检测领域的应用

[J]. 上海纺织科技, 2026, 54(3): 51-54.

[本文引用: 1]

LI Shengzhen, WANG Yang, WU Qifan.

The application of artificial intelligence technology in the textile inspection field from patent perspective

[J]. Shanghai Textile Science & Technology, 2026, 54(3): 51-54.

[本文引用: 1]

韩非, 郎晨宏, 邱夷平.

废旧纺织品循环经济的监督检验体系研究进展

[J]. 纺织学报, 2023, 44(3): 231-238.

[本文引用: 1]

HAN Fei, LANG Chenhong, QIU Yiping.

Research progress of supervision and inspection system for recycling waste textiles

[J]. Journal of Textile Research, 2023, 44(3): 231-238.

[本文引用: 1]

汪少朋, 吴宝宅, 何洲.

废旧纺织品回收与资源化再生利用技术进展

[J]. 纺织学报, 2021, 42(8): 34-40.

[本文引用: 1]

WANG Shaopeng, WU Baozhai, HE Zhou.

Technology progress in recycling and reuse of waste textiles

[J]. Journal of Textile Research, 2021, 42(8): 34-40.

[本文引用: 1]

姜涛, 段先月, 彭过房, 等.

废旧纺织品循环利用产业发展空间及促进机制

[J]. 毛纺科技, 2023, 51(6): 132-139.

[本文引用: 3]

JIANG Tao, DUAN Xianyue, PENG Guofang, et al.

Development space and promotion mechanism of waste textile recycling industry

[J]. Wool Textile Journal, 2023, 51(6): 132-139.

[本文引用: 3]

杜欢政, 陆莎, 孙荐, 等.

生活源废旧纺织品高值化回收再利用体系的构建研究

[J]. 纺织学报, 2021, 42(6): 1-7.

[本文引用: 2]

DU Huanzheng, LU Sha, SUN Jian, et al.

Research on constructing high-value recycling systems for municipal textile wastes

[J]. Journal of Textile Research, 2021, 42(6): 1-7.

DOI:10.1177/004051757204200101      URL     [本文引用: 2]

陈爽, 黄倩雯, 刘灿, 等.

废旧纺织品服装回收再利用环境影响评价综述

[J]. 现代纺织技术, 2022, 30(6): 28-36.

DOI:10.19398/j.att.202206029      [本文引用: 3]

为研究废旧纺织品服装回收再利用环境影响评价的相关问题,采用CiteSpace可视化文献分析工具,对废旧纺织品服装回收再利用环境影响评价的中英文文献进行计量分析,并讨论了废旧纺织品服装回收再利用的环境影响评价结果、再生循环的环境效益计算与分摊方法、环境影响结果综合评价等问题。结果表明:采用不同的回收工艺处理同种废旧纺织品,或将废旧纺织品再生成不同的产品,造成的环境影响具有显著差异;废旧纺织品服装再生循环的环境效益可通过扩展系统边界法进行量化,纳入再生原料的替换率和质量可提高计算精度,并可避免环境效益的主观性评价;废旧纺织品服装再生循环的环境效益在前后两个生命周期进行合理分摊,可避免环境效益的重复计算;环境影响的综合评价可实现不同再生方式环境影响的客观比较。

CHEN Shuang, HUANG Qianwen, LIU Can, et al.

Review on environmental impact assessment of waste textiles and clothing recycling

[J]. Advanced Textile Technology, 2022, 30(6): 28-36.

DOI:10.19398/j.att.202206029      [本文引用: 3]

In order to study the environmental impact assessment of waste textiles and clothing recycling, this paper adopts CiteSpace visual literature analysis tool to conduct bibliometric analysis on the Chinese and English literature on the environmental impact assessment of waste textiles and clothing recycling, and discusses the environmental impact results of waste textiles and clothing recycling, the environmental benefit calculation of recycling, the method of environmental impact sharing, and comprehensive evaluation of environmental impact. The results show that the environmental impact is significantly different when the same waste textile is treated by different recycling processes or the waste textile is regenerated into different products. The environmental benefits of the recycling of waste textiles and clothing can be obtained through the system expansion method. Including replacement rate and quality of recycled raw materials can improve the calculation accuracy and avoid subjective evaluation of environmental benefits. The environmental benefits of the recycling of waste textiles and clothing can be reasonably shared between the two life cycles, which can benefit multiple parties and avoid double-counting of environmental benefits. The comprehensive assessment of environmental impact can be characterized by value method, scoring method and geometric area method, so as to compare the overall environmental impact of different regeneration methods.

徐伟锋, 杜健.

数字技术赋能纺织产业绿色创新与发展的探讨

[J]. 棉纺织技术, 2023, 51(8): 33-37.

[本文引用: 3]

XU Weifeng, DU Jian.

Discussion on green innovation and development of textile industry enabled by digital technology

[J]. Cotton Textile Technology, 2023, 51(8): 33-37.

[本文引用: 3]

佘敏楚楚, 管丽媛, 俞建勇, 等.

新质生产力驱动下纺织行业的创新发展与转型研究

[J]. 东华大学学报(自然科学版), 2024, 50(5): 1-11.

[本文引用: 1]

SHE Minchuchu, GUAN Liyuan, YU Jianyong, et al.

Research on innovation development and transformation of textile industry driven by new quality productive forces

[J]. Journal of Donghua University (Natural Science), 2024, 50(5): 1-11.

[本文引用: 1]

纺织网.

新年新衣24小时AI快反,库存压力骤降30%

[EB/OL]. (2026-02-14)[2026-04-24]. https://info.texnet.com.cn/detail-1067828.html.

URL     [本文引用: 2]

Texindex.cn.

New year new clothes: 24-hour AI quick response reduces inventory pressure by 30%

[EB/OL]. (2026-02-14)[2026-04-24]. https://info.texnet.com.cn/detail-1067828.html.

URL     [本文引用: 2]

施乐荣, 刘荣杰, 观梦韵, 等.

基于垃圾分类的废旧纺织品的单独回收对深圳市生活垃圾处理的碳足迹影响分析

[J]. 环境卫生工程, 2018, 26(2): 4-8.

[本文引用: 1]

SHI Lerong, LIU Rongjie, GUAN Mengyun, et al.

Effects of separate recycling of household waste textile on carbon footprint of domestic waste treatment in Shenzhen based on garbage classification

[J]. Environmental Sanitation Engineering, 2018, 26(2): 4-8.

[本文引用: 1]

中华人民共和国国家互联网信息办公室.

数字化绿色化协同转型发展报告(2024)

[EB/OL]. (2024-11-30)[2026-04-24]. https://www.cac.gov.cn/2024-11/30/c_1734685875638875.htm.

URL     [本文引用: 1]

Cyberspace Administration of China.

Report on coordinated digital and green transformation development (2024)

[EB/OL]. (2024-11-30)[2026-04-24]. https://www.cac.gov.cn/2024-11/30/c_1734685875638875.htm.

URL     [本文引用: 1]

每日经济新闻.

2025新时奢·智享未来报告

[EB/OL]. (2025-03-13)[2026-04-24]. http://www.nbd.com.cn/articles/2025-03-13/3786957.htm

URL     [本文引用: 1]

National Business Daily.

2025 new era luxury·smart future report

[EB/OL]. (2025-03-13)[2026-04-24]. http://www.nbd.com.cn/articles/2025-03-13/3786957.htm

URL     [本文引用: 1]

中国发展网.

长期践行可持续发展战略,阿迪达斯荣膺2025年度财联社致远奖“环境友好(E)先锋企业奖”

[EB/OL]. (2025-11-12)[2026-04-24]. https://www.chinadevelopment.com.cn/zxsd/2025/1112/1968807.shtml.

URL     [本文引用: 1]

China Development Web.

Long-term practice of sustainable development strategy, Adidas wins the 'Environmentally Friendly (E) Pioneer Enterprise Award' of 2025 Cailianshe Zhiyuan Award

[EB/OL]. (2025-11-12)[2026-04-24]. https://www.chinadevelopment.com.cn/zxsd/2025/1112/1968807.shtml.

URL     [本文引用: 1]

人民网.

申洲针织(安徽)时尚服装智能制造项目在望江开工

[EB/OL]. (2025-04-09)[2026-04-24]. http://ah.people.com.cn/n2/2025/0409/c374164-41190606.html.

URL     [本文引用: 3]

People. cn.

Shenzhou knitting (Anhui) fashionable garment intelligent manufacturing project starts in Wangjiang

[EB/OL]. (2025-04-09)[2026-04-24].http://ah.people.com.cn/n2/2025/0409/c374164-41190606.html.

URL     [本文引用: 3]

人民网.

中国自主研发的染色新技术装备获国家科技进步一等奖

[EB/OL]. (2015-01-09)[2026-04-24]. http://politics.people.com.cn/n/2015/0109/c70731-26358891.html.

URL     [本文引用: 1]

People. cn.

China's self-developed new dyeing technology and equipment wins first prize of National Science and Technology Progress Award

[EB/OL]. (2015-01-09)[2026-04-24]. http://politics.people.com.cn/n/2015/0109/c70731-26358891.html.

URL     [本文引用: 1]

伏广伟, 张珍竹, 李红英, 等.

人工智能在纺织品检测领域的应用

[J]. 纺织报告, 2021, 40(2): 31-33, 39.

[本文引用: 1]

FU Guangwei, ZHANG Zhenzhu, LI Hongying, et al.

Application of artificial intelligence in textile testing

[J]. Jiangsu Textile, 2021, 40(2): 31-33, 39.

[本文引用: 1]

中国电信.

年检测布匹预计3亿米星辰视觉大模型AI验布机助力泉州产业焕新

[EB/OL]. (2024-06-24)[2026-04-24]. https://www.chinatelecom.com.cn/ct/news/rgzn/154054.html. CT6T=4131c0&CT6TS=1cWpWGisp_1NgGVL11JPL5isU3 O03FAFHpfh1stkXoGH8gD8T68HgIbb5d62Iy4F

URL     [本文引用: 1]

China Telecom.

Annual fabric inspection expected to reach 300 million meters - Xingchen visual large model AI fabric inspector helps Quanzhou industry renovation

[EB/OL]. (2024-06-24)[2026-04-24]. https://www.chinatelecom.com.cn/ct/news/rgzn/154054.html.

URL     [本文引用: 1]

中国纺织产业集群.

广州番禺纺织业创新智能验布机纺织品瑕疵检测准确率达97%

[EB/OL]. (2025-09-26)[2026-04-24]. http://www.ctei.cn/jq/yw/202509/t20250929_4393981.html.

URL     [本文引用: 1]

China Textile Industry Cluster.

Innovative intelligent fabric inspector in Panyu, Guangzhou achieves 97% accuracy in textile defect detection

[EB/OL]. (2025-09-26)[2026-04-24]. http://www.ctei.cn/jq/yw/202509/t20250929_4393981.html.

URL     [本文引用: 1]

郑小虎, 刘正好, 陈峰, 等.

纺织工业智能发展现状与展望

[J]. 纺织学报, 2023, 44(8): 205-216.

[本文引用: 1]

ZHENG Xiaohu, LIU Zhenghao, CHEN Feng, et al.

Current status and prospect of intelligent development in textile industry

[J]. Journal of Textile Research, 2023, 44(8): 205-216.

[本文引用: 1]

中华人民共和国国家邮政局.

全年减碳超50万吨京东物流绿色供应链带动低碳转型

[EB/OL]. (2025-05-21)[2026-04-24]. https://www.spb.gov.cn/gjyzj/c204524/202505/49b03dfa955e42fdbe09-24471b6-dac5a.shtml.

URL     [本文引用: 2]

State Post Bureau of China.

Annual carbon reduction exceeds 500,000 tons - JD Logistics green supply chain drives low-carbon transformation

[EB/OL]. (2025-05-21)[2026-04-24]. https://www.spb.gov.cn/gjyzj/c204524/202505/49b03dfa955e42fdbe0924471b6dac5a.shtml.

URL     [本文引用: 2]

中华人民共和国中央人民政府.

国务院关于修改《快递暂行条例》的决定

[EB/OL]. (2025-04-13)[2026-04-24]. https://www.gov.cn/gongbao/2025/issue_12006/202504/content_7021462.html.

URL     [本文引用: 1]

The State Council of the People's Republic of China.

Decision of the State Council on amending the Interim Regulations on Express Delivery

[EB/OL]. (2025-04-13)[2026-04-24]. https://www.gov.cn/gongbao/2025/issue_12006/202504/content_7021462.html.

URL     [本文引用: 1]

梁建芳, 程婉莹.

服装可持续消费行为的研究现状及困境分析

[J]. 丝绸, 2020, 57(6): 18-25.

[本文引用: 1]

LIANG Jianfang, CHENG Wanying.

Research on status and dilemma of sustainable clothing consumption behavior

[J]. Journal of Silk, 2020, 57(6): 18-25.

[本文引用: 1]

阿里巴巴.

阿里巴巴发布2024年ESG报告持续推进减碳与数字化普惠

[EB/OL]. (2024-07-22)[2026-04-24]. https://www.alibabagroup.com/document-1752073-403914780672.

URL     [本文引用: 1]

Alibaba.

Alibaba releases 2024 ESG report, continues to promote carbon reduction and digital inclusion

[EB/OL]. (2024-07-22)[2026-04-24]. https://www.alibabagroup.com/document-1752073-403914780672.

URL     [本文引用: 1]

孙景晓, 周立亚.

纺织服装行业可持续发展标签分析

[J]. 染整技术, 2025, 47(11): 1-6, 37.

[本文引用: 1]

SUN Jingxiao, ZHOU Liya.

Analysis of sustainability labelling in the textile and fashion industry

[J]. Textile Dyeing and Finishing Journal, 2025, 47(11): 1-6, 37.

[本文引用: 1]

邵鹏, 张媛媛.

绿色消费政策体系及对服装绿色消费的启示

[J]. 纺织学报, 2022, 43(1): 208-215.

[本文引用: 1]

SHAO Peng, ZHANG Yuanyuan.

Green consumption policy system and its enlightenment to clothing green consumption

[J]. Journal of Textile Research, 2022, 43(1): 208-215.

[本文引用: 1]

杨星, 李轻舟, 吴敏, 等.

欧盟纺织产业链上的绿色循环及废旧纺织品处理关键问题

[J]. 纺织学报, 2022, 43(1): 106-112.

[本文引用: 2]

YANG Xing, LI Qingzhou, WU Min, et al.

Circular economy in European Union textile industry chain and key issues of waste textiles treatment

[J]. Journal of Textile Research, 2022, 43(1): 106-112.

[本文引用: 2]

顾明明.

我国废旧纺织品回收利用发展现状及趋势

[J]. 环境保护, 2024, 52(11): 42-45.

[本文引用: 1]

GU Mingming.

The current situation and development trend of recycling and utilization of the textile waste in China

[J]. Environmental Protection, 2024, 52(11): 42-45.

[本文引用: 1]

新华财经.

杭州临平:新国标第四代绿色数智分拣中心投运

[EB/OL]. (2026-01-20)[2026-04-24]. https://thinktank.cnfin.com/ywdt-lb/detail/20260120/4368312_1.html.

URL     [本文引用: 1]

Xinhua Finance.

Hangzhou Linping: new national standard fourth-generation green digital intelligent sorting center put into operation

[EB/OL]. (2026-01-20)[2026-04-24]. https://thinktank.cnfin.com/ywdt-lb/detail/20260120/4368312_1.html.

URL     [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