Elemental composition is a key parameter in solid waste treatment and disposal. This study has proposed a method based on infrared spectroscopy and machine learning algorithms that can rapidly predict the elemental co...Elemental composition is a key parameter in solid waste treatment and disposal. This study has proposed a method based on infrared spectroscopy and machine learning algorithms that can rapidly predict the elemental composition (C, H, N, S) of solid waste. Both noise and moisture spectral interference that may occur in practical application are investigated. By comparing two feature selection methods and five machine learning algorithms, the most suitable models are selected. Moreover, the impacts of noise and moisture on the models are discussed, with paper, plastic, textiles, wood, and leather as examples of recyclable waste components. The results show that the combination of the feature selection and K-nearest neighbor (KNN) approaches exhibits the best prediction performance and generalization ability. Particularly, the coefficient of determination (R2) of the validation set, cross validation and test set are higher than 0.93, 0.89, and 0.97 for predicting the C, H, and N contents, respectively. Further, KNN is less sensitive to noise. Under moisture interference, the combination of feature selection and support vector regression or partial least-squares regression shows satisfactory results. Therefore, the elemental compositions of solid waste are quickly and accurately predicted under noise and moisture disturbances using infrared spectroscopy and machine learning algorithms.展开更多
Increase of sewage sludge(SS)has led to the construction of more incineration plants,exacerbating to the production of SS incineration residues.However,few studies have considered the mass balance of elements in large...Increase of sewage sludge(SS)has led to the construction of more incineration plants,exacerbating to the production of SS incineration residues.However,few studies have considered the mass balance of elements in large-scale SS incineration plants,affecting the residues treatment and utilization.In this study,flow analysis was conducted for major and trace elements in the SS,the fly ash(sewage sludge ash,SSA)and bottom ash from two large-scale SS incineration plants.The elemental characteristics were compared with those of coal fly ash(CFA),and air pollution control residues from municipal solid waste incineration(MSWIA),as well as related criteria.The results showed that the most abundant major element in SSA was Si,ranging from 120 to 240 g/kg,followed by Al(76–348 g/kg),Ca(26–113 g/kg),Fe(35–80 g/kg),and P(26–104 g/kg),and the trace elements were mainly Zn,Ba,Cu,and Mn.Not all the major elements were derived from SS.Most trace elements in the SS incineration residues accounted for 82.4%–127%of those from SS,indicating that SS was the main source of trace elements.The partitioning of heavy metals in the SS incineration residues showed that electrostatic precipitator ash or cyclone ash with high production rates were the major pollutant sinks.The differences in some major and trace elements could be indicators to differentiate SSA from CFA and MSWIA.Compared with related land criteria,the pollutants in SSA should not be ignored during disposal and utilization.展开更多
基金support from the National Key R&D Program of China(No.2020YFC1910100).
文摘Elemental composition is a key parameter in solid waste treatment and disposal. This study has proposed a method based on infrared spectroscopy and machine learning algorithms that can rapidly predict the elemental composition (C, H, N, S) of solid waste. Both noise and moisture spectral interference that may occur in practical application are investigated. By comparing two feature selection methods and five machine learning algorithms, the most suitable models are selected. Moreover, the impacts of noise and moisture on the models are discussed, with paper, plastic, textiles, wood, and leather as examples of recyclable waste components. The results show that the combination of the feature selection and K-nearest neighbor (KNN) approaches exhibits the best prediction performance and generalization ability. Particularly, the coefficient of determination (R2) of the validation set, cross validation and test set are higher than 0.93, 0.89, and 0.97 for predicting the C, H, and N contents, respectively. Further, KNN is less sensitive to noise. Under moisture interference, the combination of feature selection and support vector regression or partial least-squares regression shows satisfactory results. Therefore, the elemental compositions of solid waste are quickly and accurately predicted under noise and moisture disturbances using infrared spectroscopy and machine learning algorithms.
基金supported by the Major Science and Technology Program for Water Pollution Control and Treatment(No.2017ZX07202005)National Natural Science Foundation of China(No.21577102)。
文摘Increase of sewage sludge(SS)has led to the construction of more incineration plants,exacerbating to the production of SS incineration residues.However,few studies have considered the mass balance of elements in large-scale SS incineration plants,affecting the residues treatment and utilization.In this study,flow analysis was conducted for major and trace elements in the SS,the fly ash(sewage sludge ash,SSA)and bottom ash from two large-scale SS incineration plants.The elemental characteristics were compared with those of coal fly ash(CFA),and air pollution control residues from municipal solid waste incineration(MSWIA),as well as related criteria.The results showed that the most abundant major element in SSA was Si,ranging from 120 to 240 g/kg,followed by Al(76–348 g/kg),Ca(26–113 g/kg),Fe(35–80 g/kg),and P(26–104 g/kg),and the trace elements were mainly Zn,Ba,Cu,and Mn.Not all the major elements were derived from SS.Most trace elements in the SS incineration residues accounted for 82.4%–127%of those from SS,indicating that SS was the main source of trace elements.The partitioning of heavy metals in the SS incineration residues showed that electrostatic precipitator ash or cyclone ash with high production rates were the major pollutant sinks.The differences in some major and trace elements could be indicators to differentiate SSA from CFA and MSWIA.Compared with related land criteria,the pollutants in SSA should not be ignored during disposal and utilization.