Nirupam Chakraborti

A genetic algorithms based multi-objective neural net applied to noisy blast furnace data

A genetic algorithms based multi-objective optimization technique was utilized in the training process of a feed forward neural network, using noisy data from an industrial iron blast furnace. The number of nodes in the hidden layer, the architecture of the lower part of the network, as well as the weights used in them were kept as variables, and a Pareto front was effectively constructed by minimizing the training error along with the network size. A predator-prey algorithm efficiently performed the optimization task and several important trends were observed.

Genetic algorithms in materials design and processing

Abstract Genetic algorithms (GAs) are biologically inspired computing techniques, which tend to mimic the basic Darwinian concepts of natural selection. They are highly robust and efficient for most engineering optimising studies. Although a late entrant in the materials arena, GAs based studies are increasingly making their presence felt in many different aspects of this discipline. In recent times, GAs have been successfully used in numerous problems in the areas of atomistic material design, alloy design, polymer processing, powder compaction and sintering, ferrous production metallurgy, continuous casting, metal rolling, metal cutting, welding, and so on. The present review attempts to present the state of the art in this area. It includes three broad sections given as: fundamentals of genetic algorithms, genetic algorithms in materials design, and genetic algorithms in materials processing. The first section provides the reader with the basic concepts and the intricacies associated with this novel technique. The following section presents a detailed account of the usage of GAs to design various materials, predominantly at the atomic level. The third section aims to capture the process of applicability of GAs in numerous materials processing operations. A thorough literature search and critical analysis of the research conducted so far is provided, and attempts have been made to demonstrate how one single methodology can be utilised to study virtually every area of the vast materials discipline.

Genetic programming through bi-objective genetic algorithms with a study of a simulated moving bed process involving multiple objectives

A new bi-objective genetic programming (BioGP) technique has been developed for meta-modeling and applied in a chromatographic separation process using a simulated moving bed (SMB) process. The BioGP technique initially minimizes training error through a single objective optimization procedure and then a trade-off between complexity and accuracy is worked out through a genetic algorithm based bi-objective optimization strategy. A benefit of the BioGP approach is that an expert user or a decision maker (DM) can flexibly select the mathematical operations involved to construct a meta-model of desired complexity or accuracy. It is also designed to combat bloat - a perennial problem in genetic programming along with over fitting and under fitting problems. In this study the meta-models constructed for SMB reactors were compared with those obtained from an evolutionary neural network (EvoNN) developed earlier and also with a polynomial regression model. Both BioGP and EvoNN were compared for subsequent constrained bi-objective optimization studies for the SMB reactor involving four objectives. The results were also compared with the previous work in the literature. The BioGP technique produced acceptable results and is now ready for data-driven modeling and optimization studies at large.

Analyzing Leaching Data for Low-Grade Manganese Ore Using Neural Nets and Multiobjective Genetic Algorithms

Existing acid leaching data for low-grade manganese ores are modeled using an evolving neural net. Three distinct cases of leaching in the presence of glucose, sucrose and lactose have been considered and the results compared with an existing analytical model. The neural models are then subjected to bi-objective optimization, using a predator–prey genetic algorithm, maximizing recovery in tandem with a minimization of the acid concentration. The resulting Pareto frontiers are analyzed and discussed.

Genetic Programming Evolved through Bi-Objective Genetic Algorithms Applied to a Blast Furnace

In this study, a new Bi-objective Genetic Programming (BioGP) technique was developed that initially attempts to minimize training error through a single objective procedure and subsequently switches to bi-objective evolution to work out a Pareto-tradeoff between model complexity and accuracy. For a set of highly noisy industrial data from an operational ironmaking blast furnace (BF) this method was pitted against an Evolutionary Neural Network (EvoNN) developed earlier by the authors. The BioGP procedure was found to produce very competitive results for this complex modeling problem and because of its generic nature, opens a new avenue for data-driven modeling in many other domains.

A study of the continuous casting mold using a pareto-converging genetic algorithm

Abstract The mold region of the continuous caster, the most widely used casting device used by the steel industry has been modeled through a combination of a steady-state heat transfer approach and a recently developed pareto-converging genetic algorithm (PCGA). Due to highly non-linear nature of the objective functions, as well as the constraints, locating the pareto-front was quite a challenging job in this case. Also, from a physical consideration, the pareto-front needed to be zoomed into the region of equality of two objective functions. PCGA could successfully locate the optima after an extensive search, and the predictions are well in accord with the data provided by a number of industrial casters.

Simulating recrystallization through cellular automata and genetic algorithms

A simulation of the recrystallization process was conducted by coupling a cellular automation with a lookup table that evolved using genetic algorithms. Through an evolutionary inverse modelling, the rate of recrystallization, and the grain size distribution were successfully optimized and the recrystallized microstructure was acceptably predicted.

Regulating Crown and Flatness During Hot Rolling: A Multiobjective Optimization Study Using Genetic Algorithms

ABSTRACT A genetic algorithms-based multioptimization study has been carried out for the hot rolling practice in an integrated steel plant. The aim is to identify the parameter settings and rolling schedules that would result in the optimum values of crown and flatness–-two major parameters related to the geometric tolerances in the rolled sheet. Two objective functions and some appropriate constraints have been formulated for this purpose, and two different evolutionary algorithms are tried out on them. The optimized results are presented in the forms of Pareto fronts and discussed in the context of the actual process.

The Optimal Scheduling of a Reversing Strip Mill: Studies Using Multipopulation Genetic Algorithms and Differential Evolution

Abstract This article addresses a problem of minimizing the hot rolling time of an ingot, from a given initial thickness to a prescribed final one, subject to a number of system constraints. The idea is to determine the minimum possible odd number of passes, so that the ingot leaves in the same direction as it entered, which would ensure the necessary degree of reduction without violating the prescribed upper limits of the available torque and roll force. A maximum rolling velocity was also prescribed and additional restrictions were imposed on the rates of acceleration and deceleration inside the mill. The problem was solved by using a number of variants of genetic algorithms, including a multipopulation island model and differential evolution, besides the simple genetic algorithms. The results are compared with some earlier work based on a discrete dynamic programming technique, and a model based on an improved formulation is also presented.

Analyzing Sparse Data for Nitride Spinels Using Data Mining, Neural Networks, and Multiobjective Genetic Algorithms

Nitride spinels are typically characterized by their unique AB2N4 structure containing a divalent cation A, a trivalent cation B, and an anion N. Numerous such species may exist as metals, semiconductors, or semimetals leading to their extensive usage in diverse scientific and engineering fields. Experimental and theoretical data on the physical or material properties of nitride spinels are, however, severely limited for coming up with a data driven, generic description for their material properties. In this study we have attempted to establish a methodology for handling such sparse data where the various features of some of the state of the art soft computing tools like Genetic Algorithms, Data Mining, and Neural Networks are used in tandem to construct some generic predictive models, in principle applicable to the nitride spinel structures at large, irrespective of their electronic characteristics. The paucity of the available data was circumvented in this work with a data mining strategy, important inputs were identified through an evolving neural net, and finally, the best possible tradeoffs between the bulk moduli and the relative stabilization energies of the nitride spinels were identified by constructing the Pareto-frontier for them through a Genetic Algorithms-based multiobjective optimization strategy.