Swati Dey

Dynamic discreduction using Rough Sets

Discretization of continuous attributes is a necessary pre-requisite in deriving association rules and discovery of knowledge from databases. The derived rules are simpler and intuitively more meaningful if only a small number of attributes are used, and each attribute is discretized into a few intervals. The present research paper explores the interrelation between discretization and reduction of attributes. A method has been developed that uses Rough Set Theory and notions of Statistics to merge the two tasks into a single seamless process named dynamic discreduction. The method is tested on benchmark data sets and the results are compared with those obtained by existing state-of-the-art techniques. A real life data on TRIP steel is also analysed using the proposed method.

Rough Set Approach to Predict the Strength and Ductility of TRIP Steel

Transformation Induced Plasticity (TRIP) gives birth to new generation steels with high strength and good ductility. Both these properties of steel depend on a number of compositional and processing parameters, but till date there exist certain gaps in the understanding of the complex role of each parameters on the microstructure and thus the properties of the steel. Rough Set Theory is employed to derive decision rules that attempt to explain this complex behavior. Applying efficient heuristics, the number of attributes are reduced to form a minimal reduct, and their values are at the same time discretized into linguistic intervals. The derived rules could clearly indicate on the relative importance of the compositional and processing variables.

In silico Design of High Strength Aluminium Alloy Using Multi-objective GA

Multi-objective optimization is employed using genetic algorithm, for designing novel age-hardenable aluminium alloy with improved properties. Data on the mechanical properties of age-hardenable aluminium alloys is considered together for modeling the mechanical properties using artificial neural network. The models are used as objective functions to get the optimized combination of input parameters for the objectives, viz. high strength and ductility. The significance analyses of the variables on the ANN models gave a primary insight on the role of the variables. The Pareto solutions emerged from the GA based multi-objective optimization is found suitable for effective design of aluminium alloys with tailored properties. An in depth study of the role of the variables in the non-dominated solutions clearly describes the guideline for developing an alloy with improved mechanical properties.

Rough-Fuzzy-GA-based design of Al alloys having superior cryogenic performance

ABSTRACT Multi-objective genetic algorithm (GA) is employed for the optimal design of novel heat-treatable aluminum alloys with superior performance at cryogenic temperatures. Existing database on age-hardenable aluminum alloys is utilized to create a learning model. Composition and processing parameters of the alloys are considered as the inputs, whereas mechanical properties, viz. YS (Yield Strength), UTS (Ultimate Tensile Strength) and %Elongation tested at subzero temperatures, are used as the outputs, which characterize the performance of the alloy. Data-driven models are developed using the hybrid rough-fuzzy approach. While rough set brings out the most significant variables and formulates if-then rules to explain the relationships between inputs and outputs, fuzzy inference system (FIS) serves as the predictive model. Strength and ductility of the Al alloys at low temperature being conflicting in nature are simultaneously optimized using multi-objective GA to design alloys having an optimal blend of the two properties.

Design of patient specific dental implant using FE analysis and computational intelligence techniques

Display Omitted Genetic algorithm is successfully used for designing dental implant to achieve the desired microstrain and implant stress.Hybridization of desirability function with the ANN converted the FEA findings to make the objective.It is seen that the optimum value of microstrain differed from the desirable value with improved bone quality.The optimum solutions lead to a guideline for developing patient specific implant development.The FEA based validation of the optimum solutions shows variation of the result well within accepted limit. Genetic algorithm is employed for optimum designing of patient specific dental implants with varying dimension and porosity. It is generally recommended that, the micro strain at the bone implant interface should be around 15003000. The porous dental implant needs to be designed in such a way that the micro stain remains within the above range, and a value close to 2500 micro strain is most desired. In this design problem, the most important constraint is that the implant stress should be limited within 350MPa as titanium alloy was considered as implant material. The above attributes are to be achieved per the varying bone conditions of the patients to design a patient specific prosthesis. This design problem is expressed as an optimization problem using the desirability function, where the data generated by finite element analysis is converted to an artificial neural network model. The output of the neural network model is converted within a range of 01 using desirability function, where the maximum value is reached at the most desired micro strain of 2500. This hybrid model of neural network and desirability function is used as the objective function for the optimization problem using genetic algorithm. Another neural network model describing the implant stress is used as the constraint. The optimum solutions achieved from ANN and GA are validated again through finite element method. Without doing stress analysis by FEM, the ANN models are used for measuring the fitness of the members of the population during optimization. This would predict the optimum dimension of dental implant made of Titanium alloy with most favorable porosity percentage for better ossiointegration for a patient per bone condition.