Critical Assessment 3: The unique contributions of multi-objective evolutionary and genetic algorithms in materials research

Chakraborti, Nirupam

doi:10.1179/1743284714y.0000000578

Cited by 35 publications

(13 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [29] is an application to metallurgy. Reference [30] surveys applications to materials engineering of multi-objective genetic and evolutionary algorithms. Reference [31] discussed an application to structural damage detection.…”

Section: Aimsmentioning

confidence: 99%

An Overview of AI Methods for in-Core Fuel Management: Tools for the Automatic Design of Nuclear Reactor Core Configurations for Fuel Reload, (Re)arranging New and Partly Spent Fuel

Nissan

2019

Designs

View full text Add to dashboard Cite

An important aspect of managing a nuclear reactor is how to design refuellings, and from the 1980s to the present different artificial intelligence (AI) techniques have been applied to this problem. A section of the reactor core resembles a symmetrical grid; long fuel assemblies are inserted there, some of them new, some of them partly spent. Rods of “burnable poisons” dangle above, ready to be inserted into the core, in order to stop the reactor. Traditionally, manual design was made by shuffling positions in the grid heuristically, but AI enabled to automatically generate families of candidate configurations, under safety constraints, as well as in order to optimize combustion, with longer cycles of operation between shutdown periods, thus delaying the end-of-cycle point (except in France, where shutdown is on an annual basis, and Canada, where individual fuel assemblies are replaced, with no need for shutdown for rearranging the entire batch). Rule-based expert systems, the first being FUELCON,1 were succeeded by projects combining neural and rule-based processing (a symbolic-to-neural compilation of rules we did not implement), and later on, genetic algorithms in FUELGEN.2 In the literature, one also comes across the application of fuzzy techniques, tabu search, cellular automata and simulated annealing, as well as particle swarms. Safety regulations require simulating the results using a parameter prediction tool; this is done using either nodal algorithms, or neural processing.

show abstract

Section: Aimsmentioning

confidence: 99%

An Overview of AI Methods for in-Core Fuel Management: Tools for the Automatic Design of Nuclear Reactor Core Configurations for Fuel Reload, (Re)arranging New and Partly Spent Fuel

Nissan

2019

Designs

View full text Add to dashboard Cite

show abstract

“…The target is to create a Pareto frontier between all the six cost factors presented in Section 2. For optimization a Predator‐prey type of genetic algorithm was employed, in which a hunting game is emulated in a computational space with an implemented notion of neighborhood: a population of feasible solutions (the prey ) are pitted against a family of artificial entities (the predators ) constructed to cull the inferior (in the lesser optimal sense) members of the prey population following an optimality criterion, the Pareto optimality condition being the usual choice. In the presence of a large number of objectives, as in the present case, achieving this through any conventional multi‐objective genetic algorithms which straightway attempt to implement the Pareto concept, would be very cumbersome, if not practically impossible.…”

Section: Optimization Of the Objectivesmentioning

confidence: 99%

Multiple Criteria in a Top Gas Recycling Blast Furnace Optimized through ak-Optimality-Based Genetic Algorithm

Mohanty

Mitra

Saxén

et al. 2015

steel research int.

Self Cite

View full text Add to dashboard Cite

A steel plant flow sheet containing a top gas recycling blast furnace is simulated and subjected to multi-objective optimization through an evolutionary approach. A recently proposed k-optimality criterion is used, which allows optimizing a large number of objectives in an evolutionary way, which is difficult to do by other methods. A number of promising optimum results, showing the optimum tradeoffs between several cost factors are identified and analyzed. The results appear to be very significant in the context of CO 2 reduction challenges faced by the steel industries today.

show abstract

“…If the first solution is better than the second in at least one objective and is not worse in any objective, then the first solution is the weakly dominated solution. If these dominance conditions are not satisfied, then solutions are nondominated to each other [8,9]. All the nondominated solutions are equally good, and the decision-maker can implement any one of them.…”

Section: Introductionmentioning

confidence: 97%

Development and Multiobjective Optimization of Improved Cumene Production Processes

Flegiel

Sharma

Rangaiah

2014

Materials and Manufacturing Processes

View full text Add to dashboard Cite

Multiobjective optimization (MOO) has been successfully used to improve the process design and operation, by finding trade-offs among conflicting objectives such as energy, capital cost, and profit. In this work, the cumene process design is modified to decrease the raw materials and product losses and to facilitate better energy integration. Here, two slightly different cumene process designs are presented and evaluated. One process design uses a column to vent off the undesired chemicals, whereas the other uses two flash tanks. Additionally, vapor recompression is applied in both the designs to recover energy. Then, MOO of both modified process designs is carried out to examine two trade-offs: total capital cost (TCC) versus material loss and TCC versus utility cost. For this, an Excel-based MOO program is used; it is based on the elitist nondominated sorting genetic algorithm. The cumene process design with column is found to be superior for the first trade-off, whereas the design with two flash tanks is better for the other trade-off. Further, both the designs are compared based on their cumene production capacities; column design is found to be overall superior. Finally, energy requirements of the developed cumene process designs are compared with those reported in recent studies.

show abstract

Critical Assessment 3: The unique contributions of multi-objective evolutionary and genetic algorithms in materials research

Cited by 35 publications

References 60 publications

An Overview of AI Methods for in-Core Fuel Management: Tools for the Automatic Design of Nuclear Reactor Core Configurations for Fuel Reload, (Re)arranging New and Partly Spent Fuel

An Overview of AI Methods for in-Core Fuel Management: Tools for the Automatic Design of Nuclear Reactor Core Configurations for Fuel Reload, (Re)arranging New and Partly Spent Fuel

Multiple Criteria in a Top Gas Recycling Blast Furnace Optimized through ak-Optimality-Based Genetic Algorithm

Development and Multiobjective Optimization of Improved Cumene Production Processes

Contact Info

Product

Resources

About