Data-Driven Multiobjective Optimization for Burden Surface in Blast Furnace With Feedback Compensation

Abstract

In this paper, an intelligent data-driven optimization scheme is proposed for finding the proper burden surface distribution, which exerts large influences on keeping blast furnace running smoothly in energy-efficient state. In the proposed scheme, production indicators prediction models are firstly developed using kernel extreme learning machine algorithm. To heel, burden surface decision is presented as a multi-objective optimization problem for the first time and solved by a modified two-stage intelligent optimization strategy to generate the initial setting values of burden surface. Furthermore, considering the existence of approximation error of the created prediction models, feedback compensation is implemented to enhance the reliability of the results, in which, an improved association rules mining method is developed to find the corrected values to compensate the initial setting values. Finally, we apply the proposed optimization scheme to determine the setting values of burden surface using actual data, and experimental results illustrate its effectiveness and feasibility.

Burden Surface Decision Using MODE With TOPSIS in Blast Furnace Ironmkaing

“…The radial distribution of the charged solid raw materials, i.e., burden surface (see the right top corner of Fig. 1), influences the pressure loss and the local mass flows of solid and gas inside the furnace, and further affects the indirect reduction degree of the ore [15]. In addition, the burden surface is closely related to operating status.…”

“…Finally, the closeness coefficient C * i is calculated using Eq. (15). Ranking all the alternatives according to C * i and the optimal solution is obtained.…”

“…In terms of the optimal burden surface decision, it is basically given by the results of experience and empirical knowledge. Generally speaking, platform plus funnel mode is recognized as the ideal burden surface profile, which can satisfy the demand of gas flow distribution to achieve the improvement of gas utilization efficiency [13]- [15]. To our best knowledge, researchers rarely attempt to find the optimal burden surface matching the production status to achieve optimal key production indicators.…”

A Collaborative Optimization Strategy for Energy Reduction in Ironmaking Digital Twin

“…To analyze gas flow distribution and optimize burden distribution matrix, Huang et al composed a high temperature industrial endoscope to measure the 3D burden surface of BF [7]. Li et al found a different way to analyze the burden surface distribution by intelligent datadriven optimization scheme [8]. All of these approaches have partially explained the behaviors of BF, but the ironmaking process is in need of more information to optimize its operation strategy.…”

Model-Based Analysis of Factors Affecting the Burden Layer Structure in the Blast Furnace Shaft

“…Compared with physical experiments, mathematical modeling [3] has gained popularity due to its lower cost and higher flexibility. The mathematical modeling approaches [4,5] regarding the BF burden distribution (corresponding to the bell-less charging system) can basically be categorized as volume-based simplified models or classical (continuum) force models [6][7][8][9][10][11][12][13][14], data-driven models [15,16], or hybrid models [17,18], as well as the more computationally expensive models based of the discrete element method (DEM) [19][20][21][22][23]. Among these models, the classical force model has advantages in terms of its simple model formulation and fast computation, which are readily suitable for online implementation.…”