A Data-Driven Model for Energy Consumption in the Sintering Process

Abstract

As environmental performance becomes increasingly important, the sintering process is receiving more attention since it consumes large amounts of energy. This paper proposes a data-driven model for sintering energy consumption, which considers both model accuracy and time efficiency. The proposed model begins with removing data anomalies using a local outlier factor (LOF) algorithm and an attribute selection module using the RReliefF method. Then, to accurately predict sintering energy consumption, an integrated predictive model is employed that uses bagging-enhanced extreme learning machine (ELM) and support vector regression (SVR) machine, combined with an entropy weight method. A case study is used to demonstrate the effectiveness of the proposed model using actual production data for a year. Results show that the proposed model outperforms other models and is computationally efficient. Optimal parameters of the LOF (1.3) and number of attributes (30) were identified. It was found that coke powder has the most significant impact on the solid energy consumption (SEC), while cooling water flow rate provides the most significant impact on the gas energy consumption (GEC) within each recorded attribute variation. Parametric analysis further revealed the relationships between energy consumption and the significant attributes mentioned above. It is suggested that the proposed model could effectively reduce the energy consumption by attaining more efficient attribute settings.

A Hybrid Ensemble Model Based on ELM and Improved AdaBoost.RT Algorithm for Predicting the Iron Ore Sintering Characters

“…Scholars have made efforts to predict these characters. Wang et al [9], for instance, have constructed the data-driven energy consumption model, taking the whole manufacturing process parameters as the variables. Chen et al [10] have established the prediction model by BP neural networks, with accuracy of 91% for the comprehensive carbon efficiency.…”

Entropy-Weight-Method-Based Integrated Models for Short-Term Intersection Traffic Flow Prediction

“…Chen and Li [ 9 ] also used the same EWM to develop an integrated prediction model for unit crop yield prediction. To predict sintering energy consumption, Wang et al used this EWM to assign weights to two sintering energy consumption models [ 10 ]. For all the above papers that used EWM for model integration, the basic idea for assigning weights to different models is that if an individual model has a smaller entropy value of prediction error, the prediction variance in a model is larger, and a smaller weight should be assigned to it.…”

“…Some studies believe that a smaller information entropy value means that the data are provided by many useful attributes, so a larger weight should be assigned and vice versa [ 4 , 7 ]. On the contrary, some studies suggest that a smaller entropy value of the prediction error indicates that the variation degree and uncertainty of model prediction is greater, and thereby, a smaller weight should be assigned to this model and vice versa [ 5 , 8 , 9 , 10 ]. One recent study [ 6 ] indicates that there is a nonlinear relationship between the entropy value and model accuracy level.…”