Operating condition recognition based on temporal cumulative distribution function and AdaBoost-extreme learning machine in zinc flotation process

Author(s):  
Can Tian ◽  
Zhaohui Tang ◽  
Hu Zhang ◽  
Xiaoliang Gao ◽  
Yongfang Xie
Processes ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. 536 ◽  
Author(s):  
Zhaohui Tang ◽  
Liyong Tang ◽  
Guoyong Zhang ◽  
Yongfang Xie ◽  
Jinping Liu

It is well known that the change of the reagent dosage during the flotation process will cause the froth image to change continuously with time. Therefore, an intelligent setting method based on the time series froth image in the zinc flotation process is proposed. Firstly, the sigmoid kernel function is used to estimate the cumulative distribution function of bubble size, and the cumulative distribution function shape is characterized by sigmoid kernel function parameters. Since the reagent will affect the froth image over a period of time, the time series of bubble size cumulative distribution function is processed by the ELMo model and the dynamic feature vectors are output. Finally, XGBoost is used to establish the nonlinear relationship modeling between reagent dosage and dynamic feature vectors. Industrial experiments have proved the effectiveness of the proposed method.


Author(s):  
RONALD R. YAGER

We look at the issue of obtaining a variance like measure associated with probability distributions over ordinal sets. We call these dissonance measures. We specify some general properties desired in these dissonance measures. The centrality of the cumulative distribution function in formulating the concept of dissonance is pointed out. We introduce some specific examples of measures of dissonance.


2017 ◽  
Vol 20 (5) ◽  
pp. 939-951
Author(s):  
Amal Almarwani ◽  
Bashair Aljohani ◽  
Rasha Almutairi ◽  
Nada Albalawi ◽  
Alya O. Al Mutairi

Sign in / Sign up

Export Citation Format

Share Document