Diesel accounts for over 60%of the products derived from direct coal liquefaction(DCL).Compared to petroleum-based diesel,DCL diesel exhibits a cetane number ranging from 30 to 40,which fails to meet the automotive di...Diesel accounts for over 60%of the products derived from direct coal liquefaction(DCL).Compared to petroleum-based diesel,DCL diesel exhibits a cetane number ranging from 30 to 40,which fails to meet the automotive diesel standard requirement of≥45.Therefore,rapid and accurate analysis of its chemical composition is crucial for property optimization to meet fuel specifications by component blending.Thought traditional methods like gas chromatography offer high accuracy,they are unsuitable for rapid online analysis under industrial conditions.Near-infrared(NIR)spectroscopy can provide advantages in rapid,non-destructive analysis.Its application however,is limited by the complexity of spectral data interpretation.Machine learning(ML)is effective method for extracting valuable information from spectra and establishing high-precision prediction models.This study integrates NIR spectroscopy with ML to construct a spectral-composition database for DCL diesel.Feature extraction was performed using the correlation coefficient and mutual information methods to screen key wavelength variables and reduce data dimensionality.Subsequently,the predictive performance of three ML models—Lasso,SVR and XGBoost—was compared.Results indicate that excluding spectral data with absorbance greater than 1 significantly enhances model accuracy,increasing the test set R^(2) from 0.85 to 0.96.After feature extraction,the optimal number of wavelength variables was reduced to 177,substantially improving computational efficiency.Among the models evaluated,the SVR-MI-0.9 model,based on mutual information feature selection,demonstrated the best performance,achieving training and test set R^(2) values both exceeding 0.98.This model enables precise prediction of paraffin,naphthene,and aromatic hydrocarbon contents.This research provides a robust methodology for intelligent online quality monitoring.An intelligent NIR spectroscopy data analysis software was independently developed based on the established model.Compared with comprehensive two-dimensional gas chromatography,the software reduced the analysis time by over 98%,with an absolute prediction error below 0.2%.Thus,rapid analysis of DCL diesel components was successfully realized.展开更多
A model that rapidly predicts the density components of raw coal is described.It is based on a threegrade fast float/sink test.The recent comprehensive monthly floating and sinking data are used for comparison.The pre...A model that rapidly predicts the density components of raw coal is described.It is based on a threegrade fast float/sink test.The recent comprehensive monthly floating and sinking data are used for comparison.The predicted data are used to draw washability curves and to provide a rapid evaluation of the effect from heavy medium induced separation.Thirty-one production shifts worth of fast float/sink data and the corresponding quick ash data are used to verify the model.The results show a small error with an arithmetic average of 0.53 and an absolute average error of 1.50.This indicates that this model has high precision.The theoretical yield from the washability curves is 76.47% for the monthly comprehensive data and 81.31% using the model data.This is for a desired cleaned coal ash of 9%.The relative error between these two is 6.33%,which is small and indicates that the predicted data can be used to rapidly evaluate the separation effect of gravity separation equipment.展开更多
Linear mixed model (LMM) approaches have been widely applied in many areas of research data analysis because they offer great flexibility for different data structures and linear model systems. In this study, emphasis...Linear mixed model (LMM) approaches have been widely applied in many areas of research data analysis because they offer great flexibility for different data structures and linear model systems. In this study, emphasis is placed on comparing the properties of two LMM approaches: restricted maximum likelihood (REML) and minimum norm quadratic unbiased estimation (MINQUE) with and without resampling techniques being included. Bias, testing power, Type I error, and computing time were compared between REML and MINQUE approaches with and without Jackknife technique based on 500 simulated data sets. Results showed that MINQUE and REML methods performed equally regarding bias, Type I error, and power. Jackknife-based MINQUE and REML greatly improved power compared to non-Jackknife based linear mixed model approaches. Results also showed that MINQUE is more time-saving compared to REML, especially with the use of resampling techniques and large data set analysis. Results from the actual cotton data analysis were in agreement with our simulated results. Therefore, Jackknife-based MINQUE approaches could be recommended to achieve desirable power with reduced time for a large data analysis and model simulations.展开更多
This paper refers to the CNOP-related algorithms and formulates the practical method and forecast techniques of extracting predictable components in a numerical model for predictable components on extended-range scale...This paper refers to the CNOP-related algorithms and formulates the practical method and forecast techniques of extracting predictable components in a numerical model for predictable components on extended-range scales.Model variables are divided into predictable components and unpredictable chaotic components from the angle of model prediction error growth.The predictable components are defined as those with a slow error growth at a given range.A targeted numerical model for predictable components is established based on the operational dynamical extended-range forecast(DERF)model of the National Climate Center.At the same time,useful information in historical data are combined to find the fields for predictable components in the numerical model that are similar to those for the predictable components in historical data,reducing the variable dimensions in a similar judgment process and further correcting prediction errors of predictable components.Historical data is used to obtain the expected value and variance of the chaotic components through the ensemble forecast method.The numerical experiment results show that this method can effectively improve the forecast skill of the atmospheric circulation field in the 10–30 days extended-range numerical model and has good prospects for operational applications.展开更多
Although extended-range forecasting has exceeded the limit of daily predictability of weather,there are still partially predictable characteristics of meteorological fields in such forecasts.A targeted forecast scheme...Although extended-range forecasting has exceeded the limit of daily predictability of weather,there are still partially predictable characteristics of meteorological fields in such forecasts.A targeted forecast scheme and strategy for extended-range predictable components is proposed.Based on chaotic characteristics of the atmosphere,predictable components and unpredictable random components are separated by using the standpoint of error growth in a numerical model.The predictable components are defined as those with slow error growth at a given range,which are not sensitive to small errors in initial conditions. A numerical model for predictable components(NMPC)is established,by filtering random components with poor predictability.The aim is to maintain predictable components and avoid the influence of rapidly growing forecast errors on small scales. Meanwhile,the analogue-dynamical approach(ADA)is used to correct forecast errors of predictable components,to decrease model error and statistically take into account the influence of random components.The scheme is applied to operational dynamical extended-range forecast(DERF)model of the National Climate Center of China Meteorological Administration (NCC/CMA).Prediction results show that the scheme can improve forecast skill of predictable components to some extent, especially in high predictability regions.Forecast skill at zonal wave zero is improved more than for ultra-long waves and synoptic-scale waves.Results show good agreement with predictability of spatial scale.As a result,the scheme can reduce forecast errors and improve forecast skill,which favors operational use.展开更多
基金Supported by National Natural Science Foundation of China(U24B6018,22178243)。
文摘Diesel accounts for over 60%of the products derived from direct coal liquefaction(DCL).Compared to petroleum-based diesel,DCL diesel exhibits a cetane number ranging from 30 to 40,which fails to meet the automotive diesel standard requirement of≥45.Therefore,rapid and accurate analysis of its chemical composition is crucial for property optimization to meet fuel specifications by component blending.Thought traditional methods like gas chromatography offer high accuracy,they are unsuitable for rapid online analysis under industrial conditions.Near-infrared(NIR)spectroscopy can provide advantages in rapid,non-destructive analysis.Its application however,is limited by the complexity of spectral data interpretation.Machine learning(ML)is effective method for extracting valuable information from spectra and establishing high-precision prediction models.This study integrates NIR spectroscopy with ML to construct a spectral-composition database for DCL diesel.Feature extraction was performed using the correlation coefficient and mutual information methods to screen key wavelength variables and reduce data dimensionality.Subsequently,the predictive performance of three ML models—Lasso,SVR and XGBoost—was compared.Results indicate that excluding spectral data with absorbance greater than 1 significantly enhances model accuracy,increasing the test set R^(2) from 0.85 to 0.96.After feature extraction,the optimal number of wavelength variables was reduced to 177,substantially improving computational efficiency.Among the models evaluated,the SVR-MI-0.9 model,based on mutual information feature selection,demonstrated the best performance,achieving training and test set R^(2) values both exceeding 0.98.This model enables precise prediction of paraffin,naphthene,and aromatic hydrocarbon contents.This research provides a robust methodology for intelligent online quality monitoring.An intelligent NIR spectroscopy data analysis software was independently developed based on the established model.Compared with comprehensive two-dimensional gas chromatography,the software reduced the analysis time by over 98%,with an absolute prediction error below 0.2%.Thus,rapid analysis of DCL diesel components was successfully realized.
基金National Natural Science Foundation of China (No. 51174202)Doctoral Fund of Ministry of Education of China (No. 20100095110013)
文摘A model that rapidly predicts the density components of raw coal is described.It is based on a threegrade fast float/sink test.The recent comprehensive monthly floating and sinking data are used for comparison.The predicted data are used to draw washability curves and to provide a rapid evaluation of the effect from heavy medium induced separation.Thirty-one production shifts worth of fast float/sink data and the corresponding quick ash data are used to verify the model.The results show a small error with an arithmetic average of 0.53 and an absolute average error of 1.50.This indicates that this model has high precision.The theoretical yield from the washability curves is 76.47% for the monthly comprehensive data and 81.31% using the model data.This is for a desired cleaned coal ash of 9%.The relative error between these two is 6.33%,which is small and indicates that the predicted data can be used to rapidly evaluate the separation effect of gravity separation equipment.
文摘Linear mixed model (LMM) approaches have been widely applied in many areas of research data analysis because they offer great flexibility for different data structures and linear model systems. In this study, emphasis is placed on comparing the properties of two LMM approaches: restricted maximum likelihood (REML) and minimum norm quadratic unbiased estimation (MINQUE) with and without resampling techniques being included. Bias, testing power, Type I error, and computing time were compared between REML and MINQUE approaches with and without Jackknife technique based on 500 simulated data sets. Results showed that MINQUE and REML methods performed equally regarding bias, Type I error, and power. Jackknife-based MINQUE and REML greatly improved power compared to non-Jackknife based linear mixed model approaches. Results also showed that MINQUE is more time-saving compared to REML, especially with the use of resampling techniques and large data set analysis. Results from the actual cotton data analysis were in agreement with our simulated results. Therefore, Jackknife-based MINQUE approaches could be recommended to achieve desirable power with reduced time for a large data analysis and model simulations.
基金supported by the National Natural Science Foundation of China (Grant Nos. 40930952, 41105055)Global Change Study of Major National Scientific Research Plan of China (Grant No. 2012CB955902)Meteorological Special Project of China (Grant Nos. GYHY201106016, GYHY201106015)
文摘This paper refers to the CNOP-related algorithms and formulates the practical method and forecast techniques of extracting predictable components in a numerical model for predictable components on extended-range scales.Model variables are divided into predictable components and unpredictable chaotic components from the angle of model prediction error growth.The predictable components are defined as those with a slow error growth at a given range.A targeted numerical model for predictable components is established based on the operational dynamical extended-range forecast(DERF)model of the National Climate Center.At the same time,useful information in historical data are combined to find the fields for predictable components in the numerical model that are similar to those for the predictable components in historical data,reducing the variable dimensions in a similar judgment process and further correcting prediction errors of predictable components.Historical data is used to obtain the expected value and variance of the chaotic components through the ensemble forecast method.The numerical experiment results show that this method can effectively improve the forecast skill of the atmospheric circulation field in the 10–30 days extended-range numerical model and has good prospects for operational applications.
基金supported by National Natural Science Foundation of China (Grant Nos.41105070,40930952 and 41005041)State Key Program of Science and Technology of China(Grant No.2009BAC51B04)Meteorological Special Project of China(Grant No.GYHY 201106016)
文摘Although extended-range forecasting has exceeded the limit of daily predictability of weather,there are still partially predictable characteristics of meteorological fields in such forecasts.A targeted forecast scheme and strategy for extended-range predictable components is proposed.Based on chaotic characteristics of the atmosphere,predictable components and unpredictable random components are separated by using the standpoint of error growth in a numerical model.The predictable components are defined as those with slow error growth at a given range,which are not sensitive to small errors in initial conditions. A numerical model for predictable components(NMPC)is established,by filtering random components with poor predictability.The aim is to maintain predictable components and avoid the influence of rapidly growing forecast errors on small scales. Meanwhile,the analogue-dynamical approach(ADA)is used to correct forecast errors of predictable components,to decrease model error and statistically take into account the influence of random components.The scheme is applied to operational dynamical extended-range forecast(DERF)model of the National Climate Center of China Meteorological Administration (NCC/CMA).Prediction results show that the scheme can improve forecast skill of predictable components to some extent, especially in high predictability regions.Forecast skill at zonal wave zero is improved more than for ultra-long waves and synoptic-scale waves.Results show good agreement with predictability of spatial scale.As a result,the scheme can reduce forecast errors and improve forecast skill,which favors operational use.
