Fuzzy Byproduct Gas Scheduling in the Steel Plant Considering Uncertainty and Risk Analysis

In the iron and steel enterprises, efficient utilization of byproduct gas is of great significance for energy conservation and emission reduction. This work presents a fuzzy optimal scheduling model for byproduct gas system. Compared with previous work, uncertainties in byproduct gas systems are taken into consideration. In our model, uncertain factors in byproduct systems are described by fuzzy variables and gasholder level constraints are formulated as fuzzy chance constraints. The economy and reliability of byproduct gas system scheduling are sensitive to different confidence levels. To provide a reference for operators to determine a proper confidence level, the risk cost is defined to quantify the risk of byproduct gas shortage and emission during the scheduling process. The best confidence level is determined through the trade-off between operation cost and risk cost. The experiment results demonstrated that the proposed method can reduce the risk and give a more reasonable optimal scheduling scheme compared with deterministic optimal scheduling.

Prediction Interval Construction for Byproduct Gas Flow Forecasting Using Optimized Twin Extreme Learning Machine

Prediction of byproduct gas flow is of great significance to gas system scheduling in iron and steel plants. To quantify the associated prediction uncertainty, a two-step approach based on optimized twin extreme learning machine (ELM) is proposed to construct prediction intervals (PIs). In the first step, the connection weights of the twin ELM are pretrained using a pair of symmetric weighted objective functions. In the second step, output weights of the twin ELM are further optimized by particle swarm optimization (PSO). The objective function is designed to comprehensively evaluate PIs based on their coverage probability, width, and deviation. The capability of the proposed method is validated using four benchmark datasets and two real-world byproduct gas datasets. The results demonstrate that the proposed approach constructs higher quality prediction intervals than the other three conventional methods.