Based on data from a petrochemical company’s MIP unit over the past three years,19 input variables and 2 output variables were selected for modeling using the maximum information coefficient and Pearson correlation c...Based on data from a petrochemical company’s MIP unit over the past three years,19 input variables and 2 output variables were selected for modeling using the maximum information coefficient and Pearson correlation coefficient among 155 variables,which included properties of feedstock oil and spent catalyst,operational variables,and material flows.The distillation range variables were reduced using factor analysis,and the feedstock oils were clustered into three types using the K-means++algorithm.Each feedstock oil type was then used as an input variable for modeling.An XGBoost model and a back propagation(BP)neural network model with a structure of 20-15-15-2 were developed to predict the combined yield of gasoline and propylene,as well as the coke yield.In the test set,the BP neural network model demonstrated better fitting and generalization abilities with a mean absolute percentage error and determination coefficient of 1.48%and 0.738,respectively,compared to the XGBoost model.It was therefore chosen for further optimization work.The genetic algorithm was utilized to optimize operational variables in order to increase the combined yield of gasoline and propylene while controlling the growth of coke yield.Seven commercial test results in the MIP unit showed an average increase of 1.39 percentage points for the combined yield of gasoline and propylene and an average decrease of 0.11 percentage points for coke yield.These results indicate that the model effectively improves the combined yield of gasoline and propylene while controlling the increase in coke yield.展开更多
Using the historical simulations from 27 models in phase 5 of the Coupled Model Intercomparison Project(CMIP5)and 27 models in phase 6(CMIP6),the authors evaluated the differences between CMIP5 and CMIP6 models in sim...Using the historical simulations from 27 models in phase 5 of the Coupled Model Intercomparison Project(CMIP5)and 27 models in phase 6(CMIP6),the authors evaluated the differences between CMIP5 and CMIP6 models in simulating the climate mean of extreme temperature over China through comparison with observations during 1979–2005.The CMIP6 models reproduce well the spatial distribution of annual maxima of daily maximum temperature(TXx),annual minima of daily minimum temperature(TNn),and frost days(FD).The model spread in CMIP6 is reduced relative to CMIP5 for some temperature indices,such as TXx,warm spell duration index(WSDI),and warm days(TX90 p).The multimodel median ensembles also capture the observed trend of extreme temperature.However,the CMIP6 models still have low skill in capturing TX90 p and cold nights(TN10 p)and have obvious cold biases or warm biases over the Tibetan Plateau.The ability of individual models varies for different indices,although some models outperform the others in terms of the average of all indices considered for different models.By comparing different version models from the same organization,the updated CMIP6 models show no significant difference from their counterparts from CMIP5 for some models.Compared with individual models,the median ensembles show better agreement with the observations for temperature indices and their means.展开更多
基金the National Natural Science Foundation of China(No.U22B20141)the SINOPEC funded project(No.31900000-21-ZC0607-0009).
文摘Based on data from a petrochemical company’s MIP unit over the past three years,19 input variables and 2 output variables were selected for modeling using the maximum information coefficient and Pearson correlation coefficient among 155 variables,which included properties of feedstock oil and spent catalyst,operational variables,and material flows.The distillation range variables were reduced using factor analysis,and the feedstock oils were clustered into three types using the K-means++algorithm.Each feedstock oil type was then used as an input variable for modeling.An XGBoost model and a back propagation(BP)neural network model with a structure of 20-15-15-2 were developed to predict the combined yield of gasoline and propylene,as well as the coke yield.In the test set,the BP neural network model demonstrated better fitting and generalization abilities with a mean absolute percentage error and determination coefficient of 1.48%and 0.738,respectively,compared to the XGBoost model.It was therefore chosen for further optimization work.The genetic algorithm was utilized to optimize operational variables in order to increase the combined yield of gasoline and propylene while controlling the growth of coke yield.Seven commercial test results in the MIP unit showed an average increase of 1.39 percentage points for the combined yield of gasoline and propylene and an average decrease of 0.11 percentage points for coke yield.These results indicate that the model effectively improves the combined yield of gasoline and propylene while controlling the increase in coke yield.
基金supported by the National Key Research and Development Program of China grant number 2018YFC1509002the Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou) grant number GML2019ZD0601。
文摘Using the historical simulations from 27 models in phase 5 of the Coupled Model Intercomparison Project(CMIP5)and 27 models in phase 6(CMIP6),the authors evaluated the differences between CMIP5 and CMIP6 models in simulating the climate mean of extreme temperature over China through comparison with observations during 1979–2005.The CMIP6 models reproduce well the spatial distribution of annual maxima of daily maximum temperature(TXx),annual minima of daily minimum temperature(TNn),and frost days(FD).The model spread in CMIP6 is reduced relative to CMIP5 for some temperature indices,such as TXx,warm spell duration index(WSDI),and warm days(TX90 p).The multimodel median ensembles also capture the observed trend of extreme temperature.However,the CMIP6 models still have low skill in capturing TX90 p and cold nights(TN10 p)and have obvious cold biases or warm biases over the Tibetan Plateau.The ability of individual models varies for different indices,although some models outperform the others in terms of the average of all indices considered for different models.By comparing different version models from the same organization,the updated CMIP6 models show no significant difference from their counterparts from CMIP5 for some models.Compared with individual models,the median ensembles show better agreement with the observations for temperature indices and their means.
