Designing Evolutionary Wavelet Neural Network for Estimating Foaming Slag Quality in Electric Arc Furnace Using Power Quality Indices

In the present study,a novel approach based on an evolutionary wavelet neural network(EWNN)is proposed to estimate the slag quality in an electric arc furnace(EAF)employing power quality indices.In the EWNN,an evolutionary method is applied to train the parameters for a combination of neural networks and wavelets.I For this purpose,all of the electrical parameters for six melting processes are measured with a power quality analyzer,attached to the secondary component of an EAF transformer at a Saba steel complex,to estimate the foaming slag quality.Experimental results on various combinations of measured electrical parameters,applying the designed EWNN estimator,demonstrate that utilizing five leading indicators leads to the highest precision.The obtained 99%accuracy for estimating the foaming slag quality by EWNN compared to the other methods illustrates the proposed method's efficiency.

Slag foaming experiments in EAF for stainless steel production

The foaming slag practice can effectively solve the problems existing in EAF smelting of stainless steel, such as high electrical consumption ,high refractory consumption and long tap to tap time. In this paper, theoretical analyses were made on the technical difficulties and development feasibility of the technology. Slag foaming experiments were performed in a 10t EAF where crude stainless steel with a Cr content of 13% - 15% and a carbon content of 1.5% - 2.5% was smelted and special foaming pellets were added to release additional gas for better foaming. Good foaming slag was observed with the electric arc fully covered by the foam when the content of Cr2O3 is between 7% - 12%. The industrial scale experiments were performed in a 110 t EAF by the use of the same foaming pellets. Compared with the traditional operation, these experiments resulted in better foaming effects.

Review on monitoring and prevention technologies of splashing induced by inappropriate slag foaming in BOF

Basic oxygen steelmaking(BOS)is the most frequently used method to produce molten steel,which is being developed to meet the requirements of being safe,efficient,clean,and intelligent.During the BOS process,splashing events cause undesirable consequences,such as casualties,low efficiency,environmental pollution,and uncontrollable operation.The causes of three types of splashing(eruptive,foaming,and metallic splashing)were unraveled and it is concluded that inappropriate foaming is the root cause of splashing.A variety of monitoring techniques for splashing have been developed to measure real-time slag foaming in a basic oxygen furnace(BOF).The audiometry technique with flexible operation and high accuracy was comprehensively introduced with a practical application.Based on the formation mechanisms,the countermeasures for the three types of splashing were proposed to regulate slag foaming in a BOF by integrating diverse measures in terms of raw materials,slag forming,blowing pattern,and the use of splashing regulating agents.Future work should emphasise an automatic action for these prevention measures in response to the splashing risk from the monitoring technology,promoting the progress of intelligent steelmaking.