RESUMO
To meet the urgent need for a new design concept and solve the inaccuracy of existing performance prediction algorithms for high-speed turbomolecular pumps (TMPs), a new algorithm based on a novel twisted rotor blade is proposed. In this algorithm, the blade angle of the turbine rotor row progressively decreases from the root to the tip of the blade tooth. The feasibility and accuracy of the simulation algorithm were verified through experiments. The dependence of the simulation results on the number of simulated molecules was discussed. Both theoretical analysis and simulations confirmed the necessity of setting a twisted rotor blade in the turbine combined blade row. A comparative analysis on the performance of conventional straight-blade and twisted-blade structures based on the first-four stages of turbine combined blade rows of the F-63/55 TMP was conducted. The results indicated that the maximum pumping speed coefficient and maximum compression ratio of the optimised twisted-blade structure increased by 4.59% and 22.26%, respectively. This novel blade structure overcomes the limitations of the conventional straight-blade structure. Progressively decreasing the rotor blade angle from the root to the tip of the blade tooth is beneficial for improving the performance of TMPs. This study provides a new design concept and performance prediction algorithm for the structural optimisation of high-speed TMPs.
RESUMO
As energy efficiency becomes increasingly important to the steel industry, the iron ore sintering process is attracting more attention since it consumes the second large amount of energy in the iron and steel making processes. The present work aims to propose a prediction model for the iron ore sintering characters. A hybrid ensemble model combined the extreme learning machine (ELM) with an improved AdaBoost.RT algorithm is developed for regression problem. First, the factors that affect solid fuel consumption, gas fuel consumption, burn-through point (BTP), and tumbler index (TI) are ranked according to the attributes weightiness sequence by applying the RReliefF method. Second, the ELM network is selected as an ensemble predictor due to its fast learning speed and good generalization performance. Third, an improved AdaBoost.RT is established to overcome the limitation of conventional AdaBoost.RT by dynamically self-adjusting the threshold value. Then, an ensemble ELM is employed by using the improved AdaBoost.RT for better precision than individual predictor. Finally, this hybrid ensemble model is applied to predict the iron ore sintering characters by production data from No. 4 sintering machine in Baosteel. The results obtained show that the proposed model is effective and feasible for the practical sintering process. In addition, through analyzing the first superior factors, the energy efficiency and sinter quality could be obviously improved.