Abstract
In light of significant complexity of the byproduct gas system in steel industry (which limits an ability to establish its physics-based model), this paper proposes a data-based predictive optimization (DPO) method to carry out real-time adjusting for the gas system. Two stages of the method, namely, the prediction modeling and real-time optimization, are involved. At the prediction stage, the states of the optimized objectives, the consumption of the outsourcing natural gas and oil, the power generation, and the tank levels, are forecasted based on a proposed mixed Gaussian kernel-based prediction intervals (PIs) construction model. The Jacobian matrix of this model is represented by a kernel matrix through derivation, which greatly facilitates the subsequent calculation. At the second stage, a rolling optimization based on a mathematical programming technique involving continuous and integer decision-making variables is developed via the PIs. To demonstrate the performance of the DPO method, the practical data coming from the energy center of a steel plant are employed. The results show that the proposed DPO method can supply the human operators with effective solution for secure and economically justified optimization of the gas system.
Note to Practitioners-Given that the byproduct gas system in steel industry can hardly be described by a physics or mechanism-based model, its operation is widely realized by the experience-based manual measure at present, which exhibits a very low automation level. Since a large number of real-time energy data have been accumulated by the existing SCADA system implemented in most of steel plants, a novel data-driven real-time predictive optimization method is proposed in this study.
The proposed method aims at the short term energy optimization, thus the sample interval of the real-time data acquired from the SCADA system is set as 1 minute. The application system can provide the rolling optimized solution via real-time predicting the running circumstances of the gas system. Therefore, it is required for the plant in advance to implement the SCADA system for the energy data acquisition, and the sampling interval should be less than or equal to 1 minute. Furthermore, it is necessary for the sample data to complete the preliminary processing such as data imputation if needed since there are usually a large number of possible missing data points existed in the SCADA system of the production practice. Because such preliminary processing for the sample data belongs to a class of generic methods, this study avoids the redundant technical introduction.