每(měi)年4月22日的世界(jiè)地球日
，都(dū)提醒著(zhuó)我們(mén)關(guān)注環(huán)境問(wèn)題
，而塑(sù)料汙染無(wú)疑(yí)是其(qí)中(zhōng)一(yī)個(gè)棘(jí)手(shǒu)的挑(tiāo)戰。大量(liáng)的(dí)塑(sù)料垃圾難以(yǐ)有效回收
，傳統(tǒng)的分(fēn)選流(liú)程難以實(shí)現塑料的高純(chún)度分類
，這不僅(jǐn)是資(zī)源的(dí)巨(jù)大浪(làng)費(fèi)
，也限製(zhì)了(liǎo)再生塑(sù)料的應(yīng)用價值
，最終隻能(néng)堆積(jī)或焚燒
，對(duì)地球造成沉(chén)重(zhòng)負(fù)擔。如何(hé)才能(néng)讓(ràng)這(zhè)些廢棄的(dí)塑(sù)料“變廢(fèi)為(wéi)寶”
，以(yǐ)更高的(dí)純(chún)度回歸生產循(xún)環(huán)
，成(chéng)為(wéi)我們共同(tóng)探索的方向。

傳統(tǒng)的(dí)塑(sù)料分(fēn)選方(fāng)法
，無(wú)論是(shì)人工(gōng)操作(zuò)還是(shì)視覺相機
，都(dū)難以(yǐ)應(yīng)對(duì)日益(yì)復雜的塑料混(hùn)合物。想(xiǎng)象一(yī)下
，麵(miàn)對五花八門(mén)的(dí)塑料製品(pǐn)
，想要(yào)一(yī)一(yī)辨別(bié)它們的“真(zhēn)身(shēn)”並(bìng)精確(què)分類
，無(wú)疑是一項艱巨(jù)的(dí)任務(wù)。然而(ér)
，科技(jì)的進(jìn)步正(zhèng)在(zài)打破(pò)這(zhè)一瓶(píng)頸。

一種(zhǒng)被譽(yù)為“材(cái)料成分(fēn)鑒定(dìng)官(guān)”的技(jì)術(shù)——高(gāo)光(guāng)譜成(chéng)像
，正(zhèng)在(zài)已更高(gāo)的(dí)精(jīng)度(dù)改(gǎi)變著塑(sù)料回(huí)收的(dí)格(gé)局(jú)。這項技(jì)術(shù)通過(guò)捕捉物體(tǐ)在連續光(guāng)譜範圍內(nèi)的(dí)反射(shè)或輻(fú)射(shè)信息
，構(gòu)建(jiàn)一個包含豐(fēng)富(fù)化(huà)學(xué)成(chéng)分信息的“光譜(pǔ)指(zhǐ)紋庫(kù)”。它能(néng)夠識別(bié)出不(bù)同(tóng)塑料(liào)分(fēn)子(zǐ)的(dí)吸收(shōu)特征(zhēng)
，實現(xiàn)對微小光譜差異的高度敏感識別
，對(duì)可降解塑料(liào)也能(néng)精準區分(fēn)
，並(bìng)且這一切都(dū)可以(yǐ)在產綫上(shàng)高(gāo)速，無損(sǔn)地完成。

Every year, Earth Day on April 22nd serves as a crucial reminder to address environmental challenges, and plastic pollution stands out as a particularly thorny one. The sheer volume of plastic waste is difficult to recycle effectively. Traditional sorting methods struggle to achieve high purity levels, leading to significant resource waste and limiting the value of recycled plastic. Ultimately, much of this ends up in landfills or incinerators, placing a heavy burden on our planet. Finding ways to turn this discarded plastic into valuable resources, returning it to the production cycle with higher purity, is a shared goal we are actively pursuing.

Traditional plastic sorting methods, whether manual or standard visual cameras, are ill-equipped to handle increasingly complex plastic mixtures. Imagine trying to identify the "true identity" of a bewildering array of plastic products and sort them accurately – it's truly a tall order. However, technological advancements are breaking through this bottleneck.

Hyperspectral imaging, often dubbed a "material composition detective," is revolutionizing plastic recycling with unprecedented accuracy. This technology captures the reflectance or emission information of objects across a continuous spectral range, creating a "spectral fingerprint database" rich in chemical composition data. It can identify the absorption characteristics of different plastic molecules, enabling highly sensitive recognition of even subtle spectral differences. Biodegradable plastics can also be precisely distinguished. Crucially, all of this can be done at high speed and without damaging the material on a production line.

高(gāo)光譜可以獲得(dé)連續的(dí)光譜曲綫

Hyperspectral imaging provides continuous spectral curves

(Upper left: grayscale image, Upper right: RGB image, Lower left: multispectral image, Lower right: hyperspectral image)

這項(xiàng)技(jì)術已經(jīng)在(zài)多個(gè)應(yīng)用場景中大顯(xiǎn)身(shēn)手(shǒu)。例如(rú)
，英國倫(lún)敦(dūn)大學(xué)的研究人員采用近(jìn)紅外高光(guāng)譜技術(shù)對(duì)不同尺(chǐ)寸，不同材料的塑(sù)料樣本(běn)進行檢(jiǎn)測
，包(bāo)括可(kě)堆(duī)肥材(cái)料(liào)（甘(gān)蔗衍(yǎn)生和(hé)棕櫚葉(yè)衍(yǎn)生(shēng)），可(kě)堆肥塑(sù)料（PLA，PBAT）和傳(chuán)統塑料(liào)（PP，PET和LDPE）
，重(zhòng)點(diǎn)關注950~1730nm波段
，使(shǐ)用了主成分分(fēn)析（PCA）和偏(piān)最小二乘(chéng)判(pàn)別(bié)分析（PLS-DA）。實驗結(jié)果(guǒ)顯(xiǎn)示(shì)
，對於(yú)尺(chǐ)寸大(dà)於(yú)10毫(háo)米×10毫(háo)米的(dí)樣(yàng)品(pǐn)
，分(fēn)類(lèi)準(zhǔn)確率達到(dào)100%
，而(ér)對(duì)於較小(xiǎo)碎(suì)片
，準(zhǔn)確率(shuài)略(lüè)有下(xià)降。該結(jié)果充分(fēn)證(zhèng)明了(liǎo)高光譜(pǔ)技術(shù)在實(shí)際塑(sù)料分選中的高(gāo)效性。

This technology has already proven its mettle in various applications. For instance, researchers at University College London in the UK utilized Near-Infrared Hyperspectral Imaging (NIR-HSI) to analyze plastic samples of different sizes and materials, including compostable materials (sugarcane- and palm leaf-derived), compostable plastics (PLA, PBAT), and conventional plastics (PP, PET, and LDPE). Focusing on the 950~1730nm range and employing Principal Component Analysis (PCA) and Partial Least Squares Discriminant Analysis (PLS-DA), their experiments showed a 100% classification accuracy for samples larger than 10mm x 10mm, with a slight decrease for smaller fragments. This clearly demonstrates the high efficiency of hyperspectral technology in practical plastic sorting.

通過(guò)高光(guāng)譜(pǔ)相機獲取(qǔ)的不同(tóng)塑(sù)料的(dí)原(yuán)始吸收(shōu)光譜

Raw absorbance spectra of sugarcane derived packaging, PP, PLA, PET, LDPE, PBAT and palm leaf derived packaging acquired by hyperspectral camera

意(yì)大利的一(yī)個研究(jiū)團隊通過檢測(cè)PET，PS和PLA的主(zhǔ)要(yào)吸收峰(fēng)（分(fēn)別出(chū)現(xiàn)在(zài)1150nm至(zhì)1660nm區間）
，成功區(qū)分(fēn)了(liǎo)不同塑料(liào)類型。論文(wén)指(zhǐ)出(chū)
，這種方法能(néng)夠定量(liáng)評估分(fēn)選(xuǎn)過(guò)程的準確性
，為工(gōng)業應用提供了(liǎo)可(kě)靠(kào)依(yī)據。

An Italian research team successfully differentiated various plastic types, including PET, PS, and PLA, by detecting their main absorption peaks (occurring between 1150nm and 1660nm). Their paper highlights that this method allows for quantitative evaluation of sorting accuracy, providing a reliable basis for industrial applications.

PET樣品光譜特(tè)征 / Spectral signatures of PET samples in the NIR region

PLA樣品光(guāng)譜特征(zhēng) / Spectral signatures of PLA samples in the NIR region

PS樣(yàng)品(pǐn)光譜特征(zhēng) / Spectral signatures of PS samples in the NIR region

國(guó)內的研究(jiū)人員同樣(yàng)進(jìn)行了分(fēn)析
，結(jié)合(hé)RGB和高(gāo)光譜(pǔ)成像(xiàng)數(shù)據
，開發(fā)了一種(zhǒng)多(duō)尺度(dù)特征(zhēng)融合(hé)算法(fǎ)
，實(shí)現了對透明PET，藍(lán)色PET和(hé)透(tòu)明PP瓶(píng)的(dí)高(gāo)效(xiào)辨識(shí)
，整體(tǐ)分(fēn)類(lèi)準確(què)率達到95.55%
，而(ér)藍色(sè)PET的準確(què)率高達(dá)97.5%。這表(biǎo)明采(cǎi)用多(duō)傳(chuán)感(gǎn)器融合(hé)方法(fǎ)能夠進(jìn)一步(bù)提高分選係(xì)統的(dí)穩定(dìng)性和(hé)準確率。

Chinses researchers have also contributed significantly. By analyzing combined RGB and hyperspectral imaging data, they developed a multi-scale feature fusion algorithm to achieve efficient identification of transparent PET, blue PET, and transparent PP bottles. This resulted in an overall classification accuracy of 95.55%, with blue PET reaching an impressive 97.5%. This work indicates that integrating multiple sensors can further enhance the stability and accuracy of sorting systems.

塑(sù)料瓶的平均光(guāng)譜曲綫 / Mean spectral curve of waste plastic bottles

雜(zá)亂瓶子的分(fēn)類圖。（a）RGB 圖像(xiàng)。（b）基本(běn)實況。（c-h）分別預測了不同特征(zhēng)融(róng)合(hé)方法的(dí)分類圖。

Classification maps for cluttered bottles. (a) RGB image. (b) Ground truth. (c-h) show the classification maps predicted by different feature fusion methods, respectively.

值得一提(tí)的(dí)是
，我們也為塑(sù)料回收提(tí)供了成熟的(dí)高光譜(pǔ)解決方案(àn)。高光譜塑料識別係(xì)統集成到各(gè)類塑料(liào)分選(xuǎn)機中(zhōng)
，無論是針對整瓶還(huán)是碎片(piàn)化塑(sù)料(liào)
，都能(néng)通過數(shù)據(jù)接(jiē)口將精(jīng)準(zhǔn)的識(shí)別結(jié)果反饋(kuì)給控製係(xì)統(tǒng)
，進而通(tōng)過氣(qì)閥實(shí)現自(zì)動化的(dí)高效(xiào)分選(xuǎn)。目前(qián)
，工業(yè)高光譜(pǔ)相(xiāng)機已經(jīng)推出(chū)
，憑(píng)借其(qí)高(gāo)幀頻的(dí)特(tè)點
，能夠滿足(zú)產(chǎn)綫上快(kuài)速(sù)，連(lián)續(xù)分(fēn)選的要求。

更進(jìn)一步
，工(gōng)程(chéng)師利用(yòng)900~1700nm近紅(hóng)外(wài)高光譜(pǔ)相機(jī)對土壤中(zhōng)的微(wēi)塑料顆粒(lì)進行了識別研究
，這為解決(jué)更復雜，更貼(tiē)近實際環(huán)境(jìng)的(dí)塑(sù)料回收(shōu)提供(gōng)了重要(yào)的(dí)實(shí)驗(yàn)基礎和(hé)技術支持。

We also offer mature hyperspectral solutions for plastic recycling. Our hyperspectral plastic identification system can be integrated into various plastic sorting machines, whether for whole bottles or plastic flakes. Through data interfaces, precise identification results are relayed to the control system, enabling automated, high-efficiency sorting via air jets. Industrial hyperspectral cameras are now available, and their high frame rates are well-suited for fast, continuous sorting on production lines.

Furthermore, engineers have conducted research on identifying microplastic particles in soil using 900–1700nm near-infrared hyperspectral cameras. This provides a vital experimental foundation and technical support for tackling more complex, real-world plastic recycling challenges.

塑(sù)料分(fēn)選(xuǎn)實(shí)驗裝置及分(fēn)選結果(guǒ)

Experimental setup and sorting results for plastic separation

綜上所(suǒ)述(shù)
，高(gāo)光(guāng)譜成像技術(shù)憑借其(qí)精準(zhǔn)的(dí)材料識別能力(lì)和高效的(dí)在綫(xiàn)檢測特(tè)性
，正為(wéi)塑料(liào)回收行(háng)業(yè)注入(rù)新(xīn)的活(huó)力。這項“材(cái)料(liào)成分(fēn)鑒(jiàn)定(dìng)官(guān)”不僅能(néng)夠顯(xiǎn)著(zhù)提升回(huí)收效率(shuài)和(hé)材料(liào)純(chún)度(dù)
，更能(néng)為循(xún)環經(jīng)濟(jì)注入強(qiáng)勁(jìn)動力(lì)
，助力(lì)我們實現(xiàn)更綠色(sè)，更(gēng)可持(chí)續(xù)的未(wèi)來。讓(ràng)科技賦(fù)能(néng)回收(shōu)
，共同開啟塑(sù)料“點(diǎn)石(shí)成(chéng)金”的(dí)新篇(piān)章
！

In conclusion, hyperspectral imaging technology, with its precise material identification capabilities and efficient online inspection features, is breathing new life into the plastic recycling industry. This "material composition detective" not only significantly boosts recycling efficiency and material purity but also injects strong momentum into the circular economy. It's a game-changer that helps us move towards a greener, more sustainable future. By empowering recycling with technology, we can truly turn trash into treasure and open a new chapter in plastic recycling.

案例來(lái)源(yuán) / Source：

1. Taneepanichskul N, Hailes HC and Miodownik M (2023) Automatic identification and classification of compostable and biodegradable plastics using hyperspectral imaging. Front. Sustain. 4:1125954.

2. Moroni, M.; Mei, A. Characterization and Separation of Traditional and Bio-Plastics by Hyperspectral Devices. Appl. Sci. 2020, 10, 2800.

3. Cai, Z.; Yang, J.; Fang, H.; Ji, T.; Hu, Y.; Wang, X. Research on Waste Plastics Classification Method Based on Multi-Scale Feature Fusion. Sensors 2022, 22, 7974.