A data-driven surrogate-assisted evolutionary algorithm applied to a many-objective blast furnace optimization problem

Abstract

A new data-driven reference vector guided evolutionary algorithm has been successfully implemented to construct surrogate models for various objectives pertinent to an industrial blast furnace. A total of eight objectives have been modeled using the operational data of the furnace using twelve process variables identified through a principal component analysis and optimized simultaneously. The capability of this algorithm to handle a large number of objectives, which has been lacking earlier, results in a more efficient setting of the operational parameters of the furnace, leading to a precisely optimized hot metal production process.KEYWORDS: blast furnace, ironmaking, metamodeling, multi-objective optimization, model management, data-driven optimization, Pareto optimality INTRODUCTIONIron blast furnace is an immensely complex reactor and running it in an optimized fashion is a very complex task [1] . Although analytical models exist for this type of 2 reactors that produces hot metal [2] , such models are often quite cumbersome and of limited applicability in a real-life industrial scenario. In addition, a complete understanding of the blast furnace process involves handling several objectives together, which so far has been only marginally successful [3] . Thus, it is extremely complex, if not impossible, to build a simulator for blast furnace optimization and one has to rely upon limited amount of noisy data collected in daily operations to perform optimization.Another challenge in optimization of blast furnaces is that it involves multiple conflicting objectives, which is often known as multiobjective optimization [4] . The evolutionary algorithms have been widely used to solve multiobjective optimization problems [5] .However, the efficacy of most multiobjective evolutionary algorithms deteriorates as the number of objectives becomes more than four [4] , which makes them less suited for blast furnace optimization. Fortunately, many-objective optimization to solve problems with more than three objectives, has received increasing attention recently and many evolutionary algorithms have been developed for such problems [3,6] .Purely data-driven evolutionary optimization has received little attention with few exceptions. Most recently, Wang et al. [7] have also categorized data-driven optimization into two types: on-line and off-line. In on-line optimization, small amount of new data is available during the optimization while in off-line optimization, no extra data other than those in hands is available. The authors have also proposed a surrogate-based data-driven approach, capable of optimizing a trauma system involving two conflicting objectives in an evolutionary way. Although trauma system optimization belongs to offline data-driven 3 optimization [7] , there are a large amount of data available. By contrast, as indicated by Guo et al. [8] , off-line optimization becomes extremely challenging, when amount of historical data is small and noisy. Unfortunately, blast furnace optimization that is being...

Evolutionary Data Driven Modeling and Multi Objective Optimization of Noisy Data Set in Blast Furnace Iron Making Process

“…In the current industrial scenario, the ferrous production industries need to run the processes under very tight optimization, in order to stay competitive and continue strategies of high productivity and less emission along with the other requirements. As demonstrated in a number of recent studies [27][28][29][30][31][32][33] the use of data driven evolutionary approaches, like what has been adopted here, are clearly emerging as one of the very effective strategies to reach that goal.…”

“…A pair of objectives were taken at a time and optimized simultaneously, with various constraints. The task of maximization and minimization of the objective functions were finalized, as outlined in our previous paper . In this work, in order to make the process cost effective, the productivity was maximized with a simultaneous minimization of the coke rate.…”

“…The task of maximization and minimization of the objective functions were finalized, as outlined in our previous paper. [27] In this work, in order to make the process cost effective, the productivity was maximized with a simultaneous minimization of the coke rate. For smooth operation inside the furnace, it is necessary to minimize the tuyere cooling heat loss in order to maintain the tuyere flame temperature in the required level, so that it directly helps in maintaining the melting rate of metal and the reduction process.…”

Combined machine learning and CALPHAD approach for discovering processing-structure relationships in soft magnetic alloys

“…Machine learning approaches have been previous used to help reduce the time required in the alloy design process. [28][29][30][31][32][33][34][35][36][37][38] Supervised machine learning approaches such as artificial neural networks, [37][38][39][40] k-Nearest Neighbour algorithm (k-NN), 38,41 genetic programming, 37,38,40,42 kriging, 43,44 and unsupervised approaches such as Principal Component Analysis (PCA), 30,31,35 Hierarchical Clustering Analysis (HCA), 29,31,34 and Self Organizing Maps (SOM) 28 have been previously used in materials science and can also be helpful in this case. From an implementation point of view, there exist several open-source software packages to develop response surfaces or metamodels using several different concepts from artificial intelligence.…”

Solution Space Exploration to Design Ladle Refining Operation for Desired Downstream Requirements Using Operability Framework

“…Chugh, Chakraborti, Sindhya, and Jin discussed the challenges associated with off‐line data driven optimization in comparison to online optimization . They used a new reference vector guided evolutionary algorithm to build surrogate models for many‐objectives using operational data of a blast furnace.…”