Online Prediction Method of Molten Aluminium Height in Electrolytic Cell Based on Extreme Learning Machine with Kernel Function

An online prediction method of molten aluminium height is proposed based on extreme learning machine with kernel function (K-ELM). Firstly, relevant variables that can be measured online related to aluminium liquid fluctuations were obtained by analyzing the mechanism model of aluminium liquid fluctuations. Then, the online prediction method of molten aluminium height is proposed based on kernel function and ELM, which just use the anode-cathode voltage and the anode rod current data. Finally, the data collection and experiment of 3 sets of anode rods in the 200 kA series aluminium electrolytic cells are carried out on-site. The results show that the maximum absolute error is only 0.25 cm and relative error is less than 1.4%, which satisfied the production site requirements. Compared with existing methods, it has certain advantages in real-time and prediction accuracy and meets the real-time and accuracy requirements of the actual production process on-site.

Improving the quality of Al-Si castings by using ceramic filters

The use of cast aluminium has still increased, so have the mechanical property requirements. By casting and also in other metallurgical processes, the inclusions enter to the molten aluminium alloy and it exhibits poor ductility or toughness. It can cause a variety of problems in the manufacture of aluminium alloy castings. Therefore, the purification of the molten aluminium alloy is one of the most important processes for improving the quality of Al-products. Filters have been used for many years in order to improve the quality of castings. The inclusions in molten secondary AlSi7Mg0.3 cast were removed using depth filtration by ceramic foam filters of 20 ppi porosity. Were used 4 types of ceramic filters in 2 thicknesses (15 and 22 mm); Brinell hardness and porosity were measured. Quality of microstructure (occurrence of oxidic particles and larger non-metallic inclusions) was observed. Experimental results show that the insertion of ceramic filters into the inlet system has contributed primarily to a decrease in porosity. On the microstructure, the inclusion of filters was not significantly reflected.