Semi-supervised clustering improves learning performance as long as it uses a small number of labeled samples to assist un-tagged samples for learning.This paper implements and compares unsupervised and semi-supervise...Semi-supervised clustering improves learning performance as long as it uses a small number of labeled samples to assist un-tagged samples for learning.This paper implements and compares unsupervised and semi-supervised clustering analysis of BOA-Argo ocean text data.Unsupervised K-Means and Affinity Propagation(AP)are two classical clustering algorithms.The Election-AP algorithm is proposed to handle the final cluster number in AP clustering as it has proved to be difficult to control in a suitable range.Semi-supervised samples thermocline data in the BOA-Argo dataset according to the thermocline standard definition,and use this data for semi-supervised cluster analysis.Several semi-supervised clustering algorithms were chosen for comparison of learning performance:Constrained-K-Means,Seeded-K-Means,SAP(Semi-supervised Affinity Propagation),LSAP(Loose Seed AP)and CSAP(Compact Seed AP).In order to adapt the single label,this paper improves the above algorithms to SCKM(improved Constrained-K-Means),SSKM(improved Seeded-K-Means),and SSAP(improved Semi-supervised Affinity Propagationg)to perform semi-supervised clustering analysis on the data.A DSAP(Double Seed AP)semi-supervised clustering algorithm based on compact seeds is proposed as the experimental data shows that DSAP has a better clustering effect.The unsupervised and semi-supervised clustering results are used to analyze the potential patterns of marine data.展开更多
Two modes of gas-solid riser operation, i.e., fluid catalytic cracking (FCC) and circulating fluidized bed combustor (CFBC), have been recognized in literature; particularly in the understanding of choking phenome...Two modes of gas-solid riser operation, i.e., fluid catalytic cracking (FCC) and circulating fluidized bed combustor (CFBC), have been recognized in literature; particularly in the understanding of choking phenomena. This work compares these two modes of operation through computational fluid dynamics (CFD) simulation. In CFD simulations, the different operations are represented by fixing appropriate boundary conditions: solids flux or solids inventory. It is found that the FCC and CFBC modes generally have the same dependence of solids flux on the mean solids volume fraction or solids inventory. However, during the choking transition, the FCC mode of operation needs more time to reach a steady state; thus the FCC system may have insufficient time to respond to valve adjustments or flow state change, leading to the choking. The difference between FCC and CFBC systems is more pronounced for the systems with longer risers. A more detailed investigation of these two modes of riser operation may require a three-dimensional full loop simulation with dynamic valve adjustment.展开更多
基金This work was supported in part by the National Natural Science Foundation of China(51679105,61872160,51809112)“Thirteenth Five Plan”Science and Technology Project of Education Department,Jilin Province(JJKH20200990KJ).
文摘Semi-supervised clustering improves learning performance as long as it uses a small number of labeled samples to assist un-tagged samples for learning.This paper implements and compares unsupervised and semi-supervised clustering analysis of BOA-Argo ocean text data.Unsupervised K-Means and Affinity Propagation(AP)are two classical clustering algorithms.The Election-AP algorithm is proposed to handle the final cluster number in AP clustering as it has proved to be difficult to control in a suitable range.Semi-supervised samples thermocline data in the BOA-Argo dataset according to the thermocline standard definition,and use this data for semi-supervised cluster analysis.Several semi-supervised clustering algorithms were chosen for comparison of learning performance:Constrained-K-Means,Seeded-K-Means,SAP(Semi-supervised Affinity Propagation),LSAP(Loose Seed AP)and CSAP(Compact Seed AP).In order to adapt the single label,this paper improves the above algorithms to SCKM(improved Constrained-K-Means),SSKM(improved Seeded-K-Means),and SSAP(improved Semi-supervised Affinity Propagationg)to perform semi-supervised clustering analysis on the data.A DSAP(Double Seed AP)semi-supervised clustering algorithm based on compact seeds is proposed as the experimental data shows that DSAP has a better clustering effect.The unsupervised and semi-supervised clustering results are used to analyze the potential patterns of marine data.
基金This work is financially supported by the National Natural Science Foundation of China under Grant Nos. 91334204 and 21576263, the Chinese Academy of Sciences under Grant No. XDA07080100, and the Ministry of Science and Technology of the People's Republic of China under Grant No. 2012CB215003.
文摘Two modes of gas-solid riser operation, i.e., fluid catalytic cracking (FCC) and circulating fluidized bed combustor (CFBC), have been recognized in literature; particularly in the understanding of choking phenomena. This work compares these two modes of operation through computational fluid dynamics (CFD) simulation. In CFD simulations, the different operations are represented by fixing appropriate boundary conditions: solids flux or solids inventory. It is found that the FCC and CFBC modes generally have the same dependence of solids flux on the mean solids volume fraction or solids inventory. However, during the choking transition, the FCC mode of operation needs more time to reach a steady state; thus the FCC system may have insufficient time to respond to valve adjustments or flow state change, leading to the choking. The difference between FCC and CFBC systems is more pronounced for the systems with longer risers. A more detailed investigation of these two modes of riser operation may require a three-dimensional full loop simulation with dynamic valve adjustment.