Laser-induced breakdown spectroscopy(LIBS)has become a widely used atomic spectroscopic technique for rapid coal analysis.However,the vast amount of spectral information in LIBS contains signal uncertainty,which can a...Laser-induced breakdown spectroscopy(LIBS)has become a widely used atomic spectroscopic technique for rapid coal analysis.However,the vast amount of spectral information in LIBS contains signal uncertainty,which can affect its quantification performance.In this work,we propose a hybrid variable selection method to improve the performance of LIBS quantification.Important variables are first identified using Pearson's correlation coefficient,mutual information,least absolute shrinkage and selection operator(LASSO)and random forest,and then filtered and combined with empirical variables related to fingerprint elements of coal ash content.Subsequently,these variables are fed into a partial least squares regression(PLSR).Additionally,in some models,certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance.The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method.It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method.The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction(RMSEP)values of 1.605,3.478 and 1.647,respectively,which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables,which are 1.959,3.718 and 2.181,respectively.The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection,with RMSEP values dropping from 1.635,3.962 and 1.647 to 1.483,3.086 and 1.567,respectively.Such results demonstrate that using empirical knowledge as a support for datadriven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.展开更多
Flexural strength was monitored and predicted on the application improving concrete strength with wood and fly as partial replacement for cement.The study observed the pressure from the constituent of these locally so...Flexural strength was monitored and predicted on the application improving concrete strength with wood and fly as partial replacement for cement.The study observed the pressure from the constituent of these locally sourced material that has been observed from the study to influence the flexural strength through the effect from this locally sourced addictives.The study monitors concrete porosity on heterogeneity as it reflect on the flexural strength of self compacting concrete.Other condition considered was the compaction and placement of concrete.These effects were monitored at constant water cement ratio from design mix.The behaviour from this effects on the concrete observed the rate of flexural growth under the influences of these stated conditions.The simulation expressed the reactions of these effects through these parameters monitored to influence the system.Numerical simulations were also applied to the optimum curing age of twenty eight days,while analytical simulation was also applied.This concept is the conventional seven days interval that concrete curing were observed,these are improvement done on the study carried out by experts[16].These locally sourced material were experimentally applied.The simulation predictive values are at the interval of seven days of curing,which was also simulated.The predictive values were compared with the experimental values of the researchers[16],and both values developed best fits correlations.The study is imperative because the system considered the parameters used on experimental and observed other influential variables that were not examined.These were not observed in the experimental procedure.Experts in concrete engineering will definitely find these concept a better option in monitoring flexural strength of self compacting concrete in general.展开更多
The long-term strength retrogression of silica-enriched oil well cement poses a significant threat to wellbore integrity in deep and ultra-deep wells, which is a major obstacle for deep petroleum and geothermal energy...The long-term strength retrogression of silica-enriched oil well cement poses a significant threat to wellbore integrity in deep and ultra-deep wells, which is a major obstacle for deep petroleum and geothermal energy development. Previous attempts to address this problem has been unsatisfactory because they can only reduce the strength decline rate. This study presents a new solution to this problem by incorporating fly ash to the traditional silica-cement systems. The influences of fly ash and silica on the strength retrogression behavior of oil well cement systems directly set and cured under the condition of 200°C and 50 MPa are investigated. Test results indicate that the slurries containing only silica or fly ash experience severe strength retrogression from 2 to 30 d curing, while the slurries containing both fly ash and silica experience strength enhancement from 2 to 90 d. The strength test results are corroborated by further evidences from permeability tests as well as microstructure analysis of set cement. Composition of set cement evaluated by quantitative X-ray diffraction analyses with partial or no known crystal structure(PONKCS) method and thermogravimetry analyses revealed that the conversion of amorphous C-(A)-S-H to crystalline phases is the primary cause of long-term strength retrogression.The addition of fly ash can reduce the initial amount of C-(A)-S-H in the set cement, and its combined use with silica can prevent the crystallization of C-(A)-S-H, which is believed to be the working mechanism of this new admixture in improving long-term strength stability of oil well cement systems.展开更多
目的建立一种基于近红外光谱技术快速测定文山三七4种品质指标的方法。方法采用GB/T19086—2008《地理标志产品-文山三七》中规定的方法测定文山三七的水分、总灰分、酸不溶性灰分以及皂苷的含量,建立标杆数据。采集文山三七样品的近红...目的建立一种基于近红外光谱技术快速测定文山三七4种品质指标的方法。方法采用GB/T19086—2008《地理标志产品-文山三七》中规定的方法测定文山三七的水分、总灰分、酸不溶性灰分以及皂苷的含量,建立标杆数据。采集文山三七样品的近红外光谱数据,利用偏最小二乘回归(partial least squares regression,PLSR)方法建立模型。通过优化光谱预处理方法和变量筛选方法进一步提升模型的预测能力。结果文山三七水分、总灰分、酸不溶性灰分以及皂苷的校正集相关系数(Rc)分别为0.9891、0.9703、0.9803、0.9462,预测集相关系数(Rp)分别为0.9867、0.9678、0.9691、0.8122,预测集均方根误差(root mean square error of prediction,RMSEP)分别为0.1875、0.1405、0.0662、0.6574,性能偏差比(ratio of performance to deviation,RPD)分别为3.814、3.2300、3.9183、1.7641。结论本方法可以快速、准确地测定文山三七中4种关键品质指标,为文山三七的质量控制提供了一种快速有效的检测方法。展开更多
基金financial supports from National Natural Science Foundation of China(No.62205172)Huaneng Group Science and Technology Research Project(No.HNKJ22-H105)Tsinghua University Initiative Scientific Research Program and the International Joint Mission on Climate Change and Carbon Neutrality。
文摘Laser-induced breakdown spectroscopy(LIBS)has become a widely used atomic spectroscopic technique for rapid coal analysis.However,the vast amount of spectral information in LIBS contains signal uncertainty,which can affect its quantification performance.In this work,we propose a hybrid variable selection method to improve the performance of LIBS quantification.Important variables are first identified using Pearson's correlation coefficient,mutual information,least absolute shrinkage and selection operator(LASSO)and random forest,and then filtered and combined with empirical variables related to fingerprint elements of coal ash content.Subsequently,these variables are fed into a partial least squares regression(PLSR).Additionally,in some models,certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance.The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method.It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method.The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction(RMSEP)values of 1.605,3.478 and 1.647,respectively,which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables,which are 1.959,3.718 and 2.181,respectively.The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection,with RMSEP values dropping from 1.635,3.962 and 1.647 to 1.483,3.086 and 1.567,respectively.Such results demonstrate that using empirical knowledge as a support for datadriven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.
文摘Flexural strength was monitored and predicted on the application improving concrete strength with wood and fly as partial replacement for cement.The study observed the pressure from the constituent of these locally sourced material that has been observed from the study to influence the flexural strength through the effect from this locally sourced addictives.The study monitors concrete porosity on heterogeneity as it reflect on the flexural strength of self compacting concrete.Other condition considered was the compaction and placement of concrete.These effects were monitored at constant water cement ratio from design mix.The behaviour from this effects on the concrete observed the rate of flexural growth under the influences of these stated conditions.The simulation expressed the reactions of these effects through these parameters monitored to influence the system.Numerical simulations were also applied to the optimum curing age of twenty eight days,while analytical simulation was also applied.This concept is the conventional seven days interval that concrete curing were observed,these are improvement done on the study carried out by experts[16].These locally sourced material were experimentally applied.The simulation predictive values are at the interval of seven days of curing,which was also simulated.The predictive values were compared with the experimental values of the researchers[16],and both values developed best fits correlations.The study is imperative because the system considered the parameters used on experimental and observed other influential variables that were not examined.These were not observed in the experimental procedure.Experts in concrete engineering will definitely find these concept a better option in monitoring flexural strength of self compacting concrete in general.
基金National Natural Science Foundation of China(No.51974352 and No.52288101)China University of Petroleum(East China)(No.2018000025 and No.2019000011)。
文摘The long-term strength retrogression of silica-enriched oil well cement poses a significant threat to wellbore integrity in deep and ultra-deep wells, which is a major obstacle for deep petroleum and geothermal energy development. Previous attempts to address this problem has been unsatisfactory because they can only reduce the strength decline rate. This study presents a new solution to this problem by incorporating fly ash to the traditional silica-cement systems. The influences of fly ash and silica on the strength retrogression behavior of oil well cement systems directly set and cured under the condition of 200°C and 50 MPa are investigated. Test results indicate that the slurries containing only silica or fly ash experience severe strength retrogression from 2 to 30 d curing, while the slurries containing both fly ash and silica experience strength enhancement from 2 to 90 d. The strength test results are corroborated by further evidences from permeability tests as well as microstructure analysis of set cement. Composition of set cement evaluated by quantitative X-ray diffraction analyses with partial or no known crystal structure(PONKCS) method and thermogravimetry analyses revealed that the conversion of amorphous C-(A)-S-H to crystalline phases is the primary cause of long-term strength retrogression.The addition of fly ash can reduce the initial amount of C-(A)-S-H in the set cement, and its combined use with silica can prevent the crystallization of C-(A)-S-H, which is believed to be the working mechanism of this new admixture in improving long-term strength stability of oil well cement systems.
文摘目的建立一种基于近红外光谱技术快速测定文山三七4种品质指标的方法。方法采用GB/T19086—2008《地理标志产品-文山三七》中规定的方法测定文山三七的水分、总灰分、酸不溶性灰分以及皂苷的含量,建立标杆数据。采集文山三七样品的近红外光谱数据,利用偏最小二乘回归(partial least squares regression,PLSR)方法建立模型。通过优化光谱预处理方法和变量筛选方法进一步提升模型的预测能力。结果文山三七水分、总灰分、酸不溶性灰分以及皂苷的校正集相关系数(Rc)分别为0.9891、0.9703、0.9803、0.9462,预测集相关系数(Rp)分别为0.9867、0.9678、0.9691、0.8122,预测集均方根误差(root mean square error of prediction,RMSEP)分别为0.1875、0.1405、0.0662、0.6574,性能偏差比(ratio of performance to deviation,RPD)分别为3.814、3.2300、3.9183、1.7641。结论本方法可以快速、准确地测定文山三七中4种关键品质指标,为文山三七的质量控制提供了一种快速有效的检测方法。
