Predicting the alloying element yield in a ladle furnace using principal component analysis and deep neural network

The composition control of molten steel is one of the main functions in the ladle furnace(LF)refining process.In this study,a feasible model was established to predict the alloying element yield using principal component analysis(PCA)and deep neural network(DNN).The PCA was used to eliminate collinearity and reduce the dimension of the input variables,and then the data processed by PCA were used to establish the DNN model.The prediction hit ratios for the Si element yield in the error ranges of±1%,±3%,and±5%are 54.0%,93.8%,and98.8%,respectively,whereas those of the Mn element yield in the error ranges of±1%,±2%,and±3%are 77.0%,96.3%,and 99.5%,respectively,in the PCA-DNN model.The results demonstrate that the PCA-DNN model performs better than the known models,such as the reference heat method,multiple linear regression,modified backpropagation,and DNN model.Meanwhile,the accurate prediction of the alloying element yield can greatly contribute to realizing a“narrow window”control of composition in molten steel.The construction of the prediction model for the element yield can also provide a reference for the development of an alloying control model in LF intelligent refining in the modern iron and steel industry.

Element yield rate prediction in ladle furnace based on improved GA-ANFIS

The traditional prediction methods of element yield rate can be divided into experience method and data-driven method.But in practice,the experience formulae are found to work only under some specific conditions,and the sample data that are used to establish data-driven models are always insufficient.Aiming at this problem,a combined method of genetic algorithm(GA) and adaptive neuro-fuzzy inference system(ANFIS) is proposed and applied to element yield rate prediction in ladle furnace(LF).In order to get rid of the over reliance upon data in data-driven method and act as a supplement of inadequate samples,smelting experience is integrated into prediction model as fuzzy empirical rules by using the improved ANFIS method.For facilitating the combination of fuzzy rules,feature construction method based on GA is used to reduce input dimension,and the selection operation in GA is improved to speed up the convergence rate and to avoid trapping into local optima.The experimental and practical testing results show that the proposed method is more accurate than other prediction methods.

Growth, Metabolism and Yield of Rice Cultivated in Soils Amended with Fly Ash and Cyanobacteria and Metal Loads in Plant Parts

Soil amendment with fly ash（FA） and combined supplementation with N_2-fixing cyanobacteria masses as biofertilizer were done in field experiments with rice. Amendments with FA levels, 0, 0.5, 1.0, 2.0, 4.0, 8.0 and 10.0 kg/m2, caused increase in growth and yield of rice up to 8.0 kg/m2, monitored with several parameters. Pigment contents and enzyme activities of leaves were enhanced by FA, with the maximum level of FA at 10.0 kg/m2. Protein content of rice seeds was the highest in plants grown at FA level 4.0 kg/m2. Basic soil properties, p H value, percentage of silt, percentage of clay, water-holding capacity, electrical conductivity, cation exchange capacity, and organic carbon content increased due to the FA amendment. Parallel supplementation of FA amended plots with 1.0 kg/m2 N_2-fixing cyanobacteria mass caused further significant increments of the most soil properties, and rice growth and yield parameters. 1000-grain weight of rice plants grown at FA level 4.0 kg/m2 along with cyanobacteria supplementation was the maximum. Cyanobacteria supplementation caused increase of important basic properties of soil including the total N-content. Estimations of elemental content in soils and plant parts（root and seed） were done by the atomic absorption spectrophotometry. Accumulations of K, P, Fe and several plant micronutrients（Mn, Ni, Co, Zn and Cu） and toxic elements（Pb, Cr and Cd） increased in soils and plant parts as a function of the FA gradation, but Na content remained almost unchanged in soils and seeds. Supplementation of cyanobacteria had ameliorating effect on toxic metal contents of soils and plant parts. The FA level 4.0 kg/m2, with 1.0 kg/m2 cyanobacteria mass supplementation, could be taken ideal, since there would be recharging of the soil with essential micronutrients as well as toxic chemicals in comparative lesser proportions, and cyanobacteria mass would cause lessening toxic metal loads with usual N_2-fixation.

Compatibility of the Support System Consisting of Yielding Elements and Shotcrete Lining in Highly Faulted Grounds

The design procedure is made for a mine shaft where permanent underground facilities are interconnected. The highly faulted grounds were identified using empirical and semi-empirical theories. Furthermore, the behavior types are presented. This paper presents excavation and support methods in such ground conditions and the calculations results show that the installation of the yielding elements have an effect on support elements and prevent shotcrete damage during the curing stage. Different numerical analyses carried out showed that, with the yielding elements installed, the total displacements increase but the final axial force reduces, and therefore, the characteristic compressive strength of shotcrete is not exceeded. The calculation results of ground loads and displacements on the designed support system are presented with a 3D numerical geo-mechanical model adopted for highly faulted ground surrounding deeper complex underground structures.

Experimental study on performance of spring damping support structure system for large deformation tunnel in soft rock

According to the convergence confinement theory,it is an effective measure to control the large deformation of high ground stress in fractured soft rock tunnels by using yielding support.The yielding support can be classified as either radial or circumferential yielding support.Circumferential yielding support is achieved by transforming radial displacement into circumferential tangential closure without compromising the support capacity of the primary lining support structure.Based on this,and inspired by the design principle of dampers,a yielding support structure system with spring damping elements as its core was developed,based on the connection characteristics of steel arches in highway tunnel,which can provide increasing support resistance in the yielding deformation section.Then the mechanical properties of spring damping elements were obtained through indoor axial pressure and flexural tests.In addition,according to these results with numerical calculations,the yielding support structure system with embedded spring damping elements can reduce the internal force of the support structure by approximately 10%and increase the area of the plastic zone of the surrounding rock by 11.23%,which can fully utilize the self-bearing capacity of surrounding rock and verify the effectiveness of circumferential yielding support.Finally,the spring damping support structure system was designed with reference to the construction process of the tunnel excavated by drilling and blasting method,and the transformation of the spring damping element to spring damping support structure was achieved.Based on field test results,surrounding ground pressure for the yielding support optimization scheme was reduced by 40%and more evenly distributed,resulting in the successful application and a reduction in the construction cost of large deformation tunnels in soft rock.