The underflow concentration prediction of deep-cone thickener is a difficult problem in paste filling. The existing prediction model only determines the influence of some parameters on the underflow concentration, but...The underflow concentration prediction of deep-cone thickener is a difficult problem in paste filling. The existing prediction model only determines the influence of some parameters on the underflow concentration, but lacks a prediction model that comprehensively considers the thickening process and various factors. This paper proposed a model which analyzed the variation of the underflow concentration from a number of influencing factors in the concentrating process. It can accurately predict the underflow concentration. After preprocessing and feature selection of the history data set of the deep-cone thickener, this model uses the eXtreme gradient boosting(XGBOOST) in machine learning to deal with the relationship between the influencing factors and the underflow concentration, so as to achieve a more comprehensive prediction of the underflow concentration of the deep-cone thickener. The experimental results show that the underflow concentration prediction model based on XGBOOST shows a mean absolute error(MAE) of 0.31% and a running time of 1.6 s on the test set constructed in this paper, which fully meet the demand. By comparing the following three classical algorithms: back propagation(BP) neural network, support vector regression(SVR) and linear regression, we further verified the superiority of XGBOOST under the conditions of this study.展开更多
Baum-Welch algorithm most likely results in underflow in practice. In some literatures, such as 'Scaling' algorithm was introduced to solve the problem. In applications, however, some mistakes were found in th...Baum-Welch algorithm most likely results in underflow in practice. In some literatures, such as 'Scaling' algorithm was introduced to solve the problem. In applications, however, some mistakes were found in the equations presented in these literatures. The practical calculations show that the original algorithm often results in poor or even none convergence and rather higher error rate in speech recognition. The mistakes in these literatures and brings forward the correct equations are analysed. The speech recognition system using the revised algorithm can converge well and has lower error rate.展开更多
The analysis on the magnetic fabric of profile of the sedimentary core taken in five stations in the small spreading ridge area in Mariana Trough shows that the effect of indicating its depositional fabric, sedimentar...The analysis on the magnetic fabric of profile of the sedimentary core taken in five stations in the small spreading ridge area in Mariana Trough shows that the effect of indicating its depositional fabric, sedimentary rhythm.sedimentary events, sedimentary interfaces and sediment composition as well as sedimentary dynamic environment by magnetic. Parameters is clearer than that by traditional method of analysis. The indication of sedimentary events can show its high resolution. The study on the Late Quaternary sedimentary events in this area shows that this area underwent four big events of sudden change in the Holocene epoch based on the sudden change of underflow direction and the position relationship between ash beds and erosion sediment layers. The sudden change of underflow direction is a believable evidence for judgement and study of sudden event within this area. The direction changes of its geomagnetic field show three morphotypes i. e. relatively stable type and non-stable type of oscillatory amplitude of magnetic inclination (Inc) which existed during the relatively stable period of amplitude of magnetic declination (Dnc). Anothertype is characterized by big amplitude of both inclination and declination.The space-time series of the three type mentioned above is a new way for forming a high-resolution stratigraphical timetable.展开更多
The runoff of the Huanghe contains a great amount of suspended load and forms the high-density underflows (hyperpycnal currents) at the river mouth. The sediments over the subaqneous delta are mainly transported by th...The runoff of the Huanghe contains a great amount of suspended load and forms the high-density underflows (hyperpycnal currents) at the river mouth. The sediments over the subaqneous delta are mainly transported by the underflow. The sediment texture gradually get fining seawards, which relates to the attenuation of the hyperpycnal currents and hypopycnal plumes. Being hydraulically equivalent to the medlum-silt-sized quartz, which is the dominant component in the sediments, the clastic mica concentrates on the delta. The maximum thickness of the subaqueous delta is about 16m and the period of accumulation lasted from 12 to 16 years, therefore its sedimentary rate ranges from 110 to 130 cm/a.展开更多
基金supported by the National Key Research and Development Program of China(2016YFB0700500)the National Science Foundation of China(61572075,61702036)+1 种基金Fundamental Research Funds for the Central Universities(FRF-TP-17-012A1)China Postdoctoral Science Foundation(2017M620619)。
文摘The underflow concentration prediction of deep-cone thickener is a difficult problem in paste filling. The existing prediction model only determines the influence of some parameters on the underflow concentration, but lacks a prediction model that comprehensively considers the thickening process and various factors. This paper proposed a model which analyzed the variation of the underflow concentration from a number of influencing factors in the concentrating process. It can accurately predict the underflow concentration. After preprocessing and feature selection of the history data set of the deep-cone thickener, this model uses the eXtreme gradient boosting(XGBOOST) in machine learning to deal with the relationship between the influencing factors and the underflow concentration, so as to achieve a more comprehensive prediction of the underflow concentration of the deep-cone thickener. The experimental results show that the underflow concentration prediction model based on XGBOOST shows a mean absolute error(MAE) of 0.31% and a running time of 1.6 s on the test set constructed in this paper, which fully meet the demand. By comparing the following three classical algorithms: back propagation(BP) neural network, support vector regression(SVR) and linear regression, we further verified the superiority of XGBOOST under the conditions of this study.
文摘Baum-Welch algorithm most likely results in underflow in practice. In some literatures, such as 'Scaling' algorithm was introduced to solve the problem. In applications, however, some mistakes were found in the equations presented in these literatures. The practical calculations show that the original algorithm often results in poor or even none convergence and rather higher error rate in speech recognition. The mistakes in these literatures and brings forward the correct equations are analysed. The speech recognition system using the revised algorithm can converge well and has lower error rate.
文摘The analysis on the magnetic fabric of profile of the sedimentary core taken in five stations in the small spreading ridge area in Mariana Trough shows that the effect of indicating its depositional fabric, sedimentary rhythm.sedimentary events, sedimentary interfaces and sediment composition as well as sedimentary dynamic environment by magnetic. Parameters is clearer than that by traditional method of analysis. The indication of sedimentary events can show its high resolution. The study on the Late Quaternary sedimentary events in this area shows that this area underwent four big events of sudden change in the Holocene epoch based on the sudden change of underflow direction and the position relationship between ash beds and erosion sediment layers. The sudden change of underflow direction is a believable evidence for judgement and study of sudden event within this area. The direction changes of its geomagnetic field show three morphotypes i. e. relatively stable type and non-stable type of oscillatory amplitude of magnetic inclination (Inc) which existed during the relatively stable period of amplitude of magnetic declination (Dnc). Anothertype is characterized by big amplitude of both inclination and declination.The space-time series of the three type mentioned above is a new way for forming a high-resolution stratigraphical timetable.
基金Project supported by the National Natural Science Foundation of China.
文摘The runoff of the Huanghe contains a great amount of suspended load and forms the high-density underflows (hyperpycnal currents) at the river mouth. The sediments over the subaqneous delta are mainly transported by the underflow. The sediment texture gradually get fining seawards, which relates to the attenuation of the hyperpycnal currents and hypopycnal plumes. Being hydraulically equivalent to the medlum-silt-sized quartz, which is the dominant component in the sediments, the clastic mica concentrates on the delta. The maximum thickness of the subaqueous delta is about 16m and the period of accumulation lasted from 12 to 16 years, therefore its sedimentary rate ranges from 110 to 130 cm/a.
