Application of deep learning in iron ore sintering process:a review

In the wake of the era of big data,the techniques of deep learning have become an essential research direction in the machine learning field and are beginning to be applied in the steel industry.The sintering process is an extremely complex industrial scene.As the main process of the blast furnace ironmaking industry,it has great economic value and environmental protection significance for iron and steel enterprises.It is also one of the fields where deep learning is still in the exploration stage.In order to explore the application prospects of deep learning techniques in iron ore sintering,a comprehensive summary and conclusion of deep learning models for intelligent sintering were presented after reviewing the sintering process and deep learning models in a large number of research literatures.Firstly,the mechanisms and characteristics of parameters in sintering processes were introduced and analysed in detail,and then,the development of iron ore sintering simulation techniques was introduced.Secondly,deep learning techniques were introduced,including commonly used models of deep learning and their applications.Thirdly,the current status of applications of various types of deep learning models in sintering processes was elaborated in detail from the aspects of prediction,controlling,and optimisation of key parameters.Generally speaking,deep learning models that could be more effectively implemented in more situations of the sintering and even steel industry chain will promote the intelligent development of the metallurgical industry.

Geographical variations in risk factors associated with HIV infection among drug users in a prefecture in Southwest China

Background:Previous studies have shown inconsistent or even contradictory results for some risk factors associated with HIV infection among drug users,and these may be partially explained by geographical variations.Methods:Data were collected from 11 methadone clinics in the Liangshan Yi Autonomous Prefecture from 2004 to 2012.A non-spatial logistical regression model and a geographically weighted logistic regression model were fitted to analyze the association between HIV infection and specific factors at the individual level.Results:This study enrolled 6,458 patients.The prevalence of HIV infection was 25.1%.The non-spatial model indicated that being divorced was positively associated with HIV infection.The spatial model also showed that being divorced was positively associated with HIV infection,but only for 49.4%of individuals residing in some northern counties.The non-spatial model suggested that service sector work was negatively associated with HIV infection.However,the spatial model indicated that service work was associated with HIV infection,but only for 23.0%of patients living in some western counties.The non-spatial model did not show that being married was associated with HIV infection in our study field,but the spatial model indicated that being married was negatively associated with HIV infection for 12.0%of individuals living in some western counties.For other factors,the non-spatial and spatial models showed similar results.Conclusion:The spatial model may be useful for improving understanding of geographical heterogeneity in the relationship between HIV infection and individual factors.Spatial heterogeneity may be useful for tailoring intervention strategies for local regions,which can consequently result in a more efficient allocation of limited resources toward the control of HIV transmission.