|
|
|
|
|
|
Research on Deep Sorting Approach Based on Infrared Spectroscopy for High-Value Utilization of Municipal Solid Waste |
HU Bin1, 2, FU Hao1, WANG Wen-bin1, ZHANG Bing1, 2, TANG Fan3*, MA Shan-wei1, 2, LU Qiang1, 2* |
1. School of New Energy, North China Electric Power University, Beijing 102206, China
2. National Engineering Laboratory for Biomass Power Generation Equipment, North China Electric Power University, Beijing
102206, China
3. School of Artificial Intelligence, Jilin University, Changchun 130012, China
|
|
|
Abstract Due to the advantages of high speed and high accuracy, infrared spectra play a vital role in classification and identification. For municipal solid wastes, the application of infrared spectra mainly focuses on recyclable garbage such as plastics, neglecting the deep separation of the non-recyclable wastes. Based on the current “Quartering Method” of municipal solid wastes, the residual wastes contain various high-value potential ingredients that can be sorted into cellulose, vinyl-polymers, and woods. These ingredients have different constituents and structures, so they have different infrared spectra. Therefore, the useful constituents can be further separated from the residual wastes by combing their infrared spectra and the machine learning classification models. This study collected cellulose, vinyl-polymers, woods, and low-value residual wastes, and 72 groups of infrared spectra data were obtained. The influence of data preprocessing, dimension reduction and algorithms on the sorting models’ accuracy was investigated. Infrared spectra data were preprocessed by standard normal variate (SNV), multiplicative scatter correction (MSC), derivative correction (DC), and smooth. Principal component analysis (PCA) was used to reduce the dimension of the preprocessed data, and 72×8 and 72×5 datasets were obtained. Sorting models were built using probabilistic neural network (PNN), generalized regression neural network (GRNN), support vector machine (SVM), and random forest (RDF) algorithms. As a result, the classification accuracy of 5-Dimensional data was superior to that of 8-Dimensional data, with the average accuracy increasing 2.4%~4.4%. Based on 5-Dimensional data, DC/Smooth preprocessing achieved the highest average accuracy of 96.5% among the three preprocessing methods. The average accuracy of the PNN model was 4.2%~6.5% higher than the other three sorting models, up to 98.1%. As for the four types of residual wastes, the sorting accuracy for vinyl polymers was 93.8%, it was over 95% for cellulose and woods, and it could be up to 100% for the low-value wastes. This study examined the possibility and scientific potentiality of the combination of infrared spectroscopy and machine learning to achieve the deep sorting of residual wastes, providing a theoretical basis for the future development of fast and accurate deep separation equipment of municipal solid wastes.
|
Received: 2021-03-01
Accepted: 2021-07-27
|
|
Corresponding Authors:
TANG Fan, LU Qiang
E-mail: tfan.108@gmail.com;qianglu@mail.ustc.edu.cn
|
|
[1] CHU Xiao-li, CHEN Pu, LI Jing-yan, et al(褚小立, 陈 瀑, 李敬岩, 等). Journal of Instrumental Analysis(分析测试学报), 2020, 39(10): 1181.
[2] Bec Krzysztof B, Grabska Justyna, Huck Christian W. Analytica Chimica Acta, 2020, 1133: 150.
[3] LIU Wei-lai, JIA Si-liang, LIU Jing(刘维来, 贾思良, 刘 静). Environmental Engineering(环境工程), 2019, 37(5): 293.
[4] LIU Yan-de, XIAO Huai-chun, DENG Qing, et al(刘燕德, 肖怀春, 邓 清, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2019, 32(40): 202.
[5] PAN Xi, LIU Hui, WANG Hao, et al(潘 曦, 刘 辉, 王 昊, 等). Journal of Instrumental Analysis(分析测试学报), 2020, 39(11): 1385.
[6] YIN Feng-fu, YAN Lei, HAN Qing-xin, et al(尹凤福, 闫 磊, 韩清新, 等). Environmental Engineering(环境工程), 2017, 35(12): 134.
[7] ZHAO Dong-e, WU Rui, ZHAO Bao-guo, et al(赵冬娥, 吴 瑞, 赵宝国, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(3): 921.
[8] YUAN Jing-zhu, ZHU Tong(袁惊柱, 朱 彤). Energy of China(中国能源), 2018, 40(6): 16.
[9] QIAN Le, JIANG Li-qun, YUE Yuan-mao, et al(钱 乐, 蒋丽群, 岳元茂, 等). CIESC Journal(化工学报), 2020, 71(12): 5376.
[10] LAN Mei-chen, SHEN Bo-xiong, WANG Jian-qiao, et al(兰美晨, 沈伯雄, 王建桥, 等). Journal of Fuel Chemistry and Technology(燃料化学学报), 2019, 47(11): 1313.
[11] Shafaghat H, Sirous-Rezaei P, Daud W M A. Journal of Industrial and Engineering Chemistry, 2016, 35: 268.
[12] ZHAO Yue-shu, XUE Xiao-ming, SONG Xiao-jiao, et al(赵阅书, 薛晓明, 宋小娇, 等). Journal of Forestry Engineering(林业工程学报), 2019, 4(5): 40.
[13] WEI Chen-jie, WANG Ji-fen, JI Jia-hua, et al(卫辰洁, 王继芬, 季佳华, 等). Chemical Research and Application(化学研究与应用), 2021, 33(2): 269.
[14] Saeys W, Do Trong N N, Van Beers R, et al. Postharvest Biology and Technology, 2019, 158: 110981.
[15] Porizka Pavel, Klus Jakub, Kepes E, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2018, 148: 65.
|
[1] |
LI Jia-wang, LIU Yan, ZHANG De-qing, YANG Yong-an, ZHANG Chuan-yun, LI Lun, SI Min-zhen*. Comparison and Analysis of IR Spectra of Four Dendrobium Species[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 2989-2994. |
[2] |
LI Yuan1, ZHANG Wen-bo1, CHEN Xiao-lin2, 3, LI Han1, ZHANG Guan-jun1. Application of Gaussian Process Regression on the Quantitative Analysis of the Aging Condition of Insulating Paper by Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3073-3078. |
[3] |
WU Bin1, SHEN Jia-qi2, WANG Xin2, WU Xiao-hong3, HOU Xiao-lei2. NIR Spectral Classification of Lettuce Using Principal Component
Analysis Sort and Fuzzy Linear Discriminant Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3079-3083. |
[4] |
ZHANG Xu1, YAN Yue-er1*, ZHANG Chun-mei2*, YANG Guang-hui1, TANG Yi3. Non-Destructive Analysis of Yan’an Red Literature by FTIR Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3097-3102. |
[5] |
YANG Dong-feng1, LI Ai-chuan1, LIU Jin-ming1, CHEN Zheng-guang1, SHI Chuang1, HU Jun2*. Optimization of Seed Vigor Near-Infrared Detection by Coupling Mean Impact Value With Successive Projection Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3135-3142. |
[6] |
YUAN Ke-yan 1, WANG Rong2, WANG Xiang-xiang2, XUE Li-ping2, YU Li2*. Identification and Restoration of Pseudo-Hydrolyzed Animal Protein of Lacteus Camelus Based on iPLS Model of Near-Infrared Measurement Spectrum of 6 mm Detection Plate[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3143-3147. |
[7] |
HU Guo-tian1, 2, 3, SHANG Hui-wei1, 2, 3, TAN Rui-hong1, XU Xiang-hu1, PAN Wei-dong1. Research on Model Transfer Method of Organic Matter Content
Estimation of Different Soils Using VNIR Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3148-3154. |
[8] |
TIAN Jia-yi, MA Fang, HAN Ling-yu*. Analysis of Composition Differences of Fresh Radix Rehmanniae, Crude Radix Rehmanniae and Processed Radix Rehmanniae Using Infrared
Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3203-3209. |
[9] |
ZHANG Fu1, 2, 3, WANG Xin-yue2, CUI Xia-hua2, CAO Wei-hua2, ZHANG Xiao-dong1*, ZHANG Ya-kun2. Classification of Qianxi Tomatoes by Visible/Near Infrared Spectroscopy Combined With GMO-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3291-3297. |
[10] |
HU Yun-you1, 2, XU Liang1*, XU Han-yang1, SHEN Xian-chun1, SUN Yong-feng1, XU Huan-yao1, 2, DENG Ya-song1, 2, LIU Jian-guo1, LIU Wen-qing1. Adaptive Matched Filter Detection for Leakage Gas Based on Multi-Frame Background[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3307-3313. |
[11] |
HU Xin-yu1, 2, XU Zhang-hua1, 2, 3, 5, 6*, HUANG Xu-ying1, 2, 8, ZHANG Yi-wei1, 2, CHEN Qiu-xia7, WANG Lin1, 2, LIU Hui4, LIU Zhi-cai1, 2. Relationship Between Chlorophyll and Leaf Spectral Characteristics and Their Changes Under the Stress of Phyllostachys Praecox[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2726-2739. |
[12] |
LIU Jin, FU Run-juan, HAN Tong-shuai*, LIU Rong, SUN Di. Spectral Analysis of Human Tissues Based on a Direct Effective
Attenuation Coefficient Measurement[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2746-2751. |
[13] |
LI Zi-xuan1, LIU Hong2, ZHANG Yan-dong1, WU Xiao-jing1*, CHENG Long-jiu3. Study on Phase Transition of Myristic Acid by Two-Dimensional Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2763-2767. |
[14] |
BAI Zi-jin1, PENG Jie1*, LUO De-fang1, CAI Hai-hui1, JI Wen-jun2, SHI Zhou3, LIU Wei-yang1, YIN Cai-yun1. A Mid-Infrared Spectral Inversion Model for Total Nitrogen Content of Farmland Soil in Southern Xinjiang[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2768-2773. |
[15] |
XU Lu1, CHEN Yi-yun1, 2, 3*, HONG Yong-sheng1, WEI Yu1, GUO Long4, Marc Linderman5. Estimation of Soil Organic Carbon Content by Imaging Spectroscopy With Soil Roughness[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2788-2794. |
|
|
|
|