scholarly journals Multi-objective optimization of magnetic abrasive finishing by desirability function with genetic algorithm

2021 ◽  
Vol 13 (1) ◽  
pp. 1-9
Author(s):  
Rajneesh Kumar Singh ◽  
Swati Gangwar ◽  
D.K. Singh ◽  
Shadab Ahmad
Keyword(s):  
Genetic Algorithm ◽  
Function Analysis ◽  
Desirability Function ◽  
Fitness Function ◽  
Hybrid Approach ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Finished Surface ◽  
En 31 ◽  
Desirability Function Analysis

Thermal stability and Surface hardness of the super-finished surface is a very important aspect to preserve the surface texture of workpiece in the MAF process. In this present study, the multi-objective optimization of EN-31 finished through the MAF process. “Increase in Temperature” and “Increase in Hardness” are considered for optimization to diminish their impact on the super-finished surface of EN-31. In present work Desirability function analysis (DFA) has been used to optimize the desired responses of the MAF process. Experiments were designed according to Taguchi L9 orthogonal array for the finishing of EN-31. The experiment results are processed using DFA and Desirability fitness function is established to convert the single response to multi-response. Genetic Algorithm (GA) is used to enhance the results of DFA and the regression model was developed to obtain the objective function of Genetic algorithm. Smaller-the-best criteria were used for ‘Increase in Temperature’ and ‘Increase in Hardness’ for obtaining favorable process parameters. The best optimal parametric combination is obtained by using the GA-DFA hybrid approach is at 2.5 mm (working gap), 20 gm (abrasive weight), and 2.0 A (Current) and 300 rpm (rotational speed).  

scholarly journals Multi-Objective Optimization of Properties of Sponge Gourd-Bagasse Hybrid Reinforced Polymer Composite Using Fuzzy Logic, PSO, Modified Desirability Function and NSGA II

2021 ◽  
Author(s):  
Ikechukwu Chibueze ◽  
Chizoba Obele ◽  
CHIDOZIE NWOBI-OKOYE ◽  
Clement Atuanya
Keyword(s):  
Mechanical Properties ◽  
Fuzzy Logic ◽  
Computational Models ◽  
Desirability Function ◽  
Fitness Function ◽  
Golf Club ◽  
Multi Objective Optimization ◽  
Nsga Ii ◽  
Multi Objective ◽  
Sponge Gourd

Abstract Development of mathematical models for prediction of properties of materials is often complex and cumbersome. This led to the advent of simpler, and often more accurate, computational models based on artificial intelligence for predicting materials properties. The aim of this study is to predict the mechanical properties of a newly developed hybrid composite material made with sponge gourd, baggase and epoxy resin for golf club application using fuzzy logic (FL) and carry out a multi-objective optimization of the properties with modified desirability function (DF) and NSGA II algorithm. The inputs were %Wt of baggase, %Wt of Sponge gourd and Fiber size (µm) while the response variables were tensile strength, hardness, flexural strength, modulus, elongation and impact strength. The FL model was separately coupled, as fitness function, with the modified DF algorithm and the NSGA II algorithm respectively. The DF was optimized with particle swarm optimization (PSO) algorithm. The results showed that the FL model predicted the mechanical properties accurately and the minimum correlation coefficient (R) between the experimental responses and FL predictions was 0.9529. The modified algorithms took care of certain peculiarities in the desirability properties such as elongation whose desirability is constant over a range. The optimized properties were found to be worse if the optimization algorithms were not modified.

Exploration of Desirability Function Analysis-Based Particle Swarm Optimization for Magnetic Abrasive Finishing of Mild Steel

2020 ◽  
Vol 19 (04) ◽  
pp. 607-627
Author(s):  
Rajneesh Kumar Singh ◽  
Swati Gangwar ◽  
D. K. Singh
Keyword(s):  
Particle Swarm Optimization ◽  
Mild Steel ◽  
Function Analysis ◽  
Desirability Function ◽  
Heuristic Optimization ◽  
Optimization Approach ◽  
Swarm Optimization ◽  
Abrasive Finishing ◽  
Finished Surface ◽  
Desirability Function Analysis

Analysis of surface roughness, temperature and hardness of the finished surface is beneficial to retain the desired surface finish of the workpiece via the magnetic abrasive finishing (MAF) process. In this work, “change in roughness” ([Formula: see text]Ra), “raise in temperature” ([Formula: see text]) and “change in hardness” ([Formula: see text]) were opted for the multi-objective meta-heuristic optimization to minimize their impact on the finished surface of mild steel. Taguchi [Formula: see text] orthogonal array was used to obtain the experimental data on mild steel. The desirability fitness function (DFF) was developed to convert multi-responses to a single response. Finally, particle swarm optimization (PSO) was used for a higher-level decision-making and a meta-heuristic optimization approach, i.e. desirability function analysis-based PSO (PSO-DFA), was developed to obtain the best performance condition for surface finish. The best optimal setting obtained by using PSO-DFA included a working gap of 1.5[Formula: see text]mm, an abrasive weight of 15[Formula: see text]g, a voltage of 6[Formula: see text]V and a rotational speed of 50[Formula: see text]rpm. This setting has been selected based on the highest PSO-DFA value predicted by the meta-heuristic optimization approach and improved by 38.20% in comparison with DFA, that shows a satisfactory performance.

Multi-Objective Optimization of Stacking Sequences for Laminated Composite Beams by Genetic Algorithm

2015 ◽  
Vol 729 ◽  
pp. 89-94
Author(s):  
Fatih Karaçam ◽  
Taner Timarci
Keyword(s):  
Genetic Algorithm ◽  
Fitness Function ◽  
Optimization Technique ◽  
Orientation Angle ◽  
Laminated Composite ◽  
Beam Theory ◽  
Composite Beams ◽  
Function Optimization ◽  
Multi Objective Optimization ◽  
Multi Objective

In this study, multi-objective optimization of stacking sequences for laminated composite composite beams is studied for simply supported boundary conditions. A unified three-degrees-of-freedom shear deformable beam theory is used for analytical solution and genetic algorithm is used as optimization technique. By use of two different parameters such as the deflection and frequency together in a pre-defined fitness function, optimization process is carried out in order to maximize the fitness function. Initially, the deflection, frequency, fitness function values and corresponding stacking sequences are presented for various number of layers and increment of fiber orientation angle. The variation of the fitness function with respect to deflection and frequency depending on the number of generations are presented.

MULTI-OBJECTIVE OPTIMIZATION IN RELIABILITY SYSTEM USING GENETIC ALGORITHM AND NEURAL NETWORK

2008 ◽  
Vol 25 (05) ◽  
pp. 649-672 ◽  
Author(s):  
LIANG-HSUAN CHEN ◽  
CHENG-HSIUNG CHIANG
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Optimization Problems ◽  
Hybrid Approach ◽  
System Optimization ◽  
Evolutionary Strategy ◽  
Initial Population ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Reliability Systems

To optimize the design of reliability systems, an analyst is frequently faced with the demand of achieving several targets (i.e., maximization of system reliability, minimizations of cost, volume, and weight), some of which may be in conflict with each other. This paper presents a novel hybrid approach, combining a multi-objective genetic algorithm and a neural network, for multi-objective optimization of a reliability system, namely GANNRS (Genetic Algorithm and Neural Network for Reliability System optimization). The multi-objective genetic algorithm's evolutionary strategy is based on the modified neighborhood design, and is presented to find the Pareto optimal solutions so as to provide a variety of compromise solutions to the decision makers. The purpose of the neural network is to generate a good initial population in order to speed up the searching by genetic algorithm. For demonstrating the feasibility of the proposed approach, four multi-objective optimization problems of reliability system are used, and the outcomes are compared with those from other methods. The evidence shows that the proposed GANNRS is more efficient in computation, and the results from the objectives are appealing.

MULTI-OBJECTIVE OPTIMIZATION OF OFFSHORE TSUNAMI OBSERVATION POINTS BY GENETIC ALGORITHM

2020 ◽  
Vol 76 (2) ◽  
pp. I_325-I_330
Author(s):  
Kazutoshi KURAMOTO ◽  
Fumiyasu MAKINOSHIMA ◽  
Anawat SUPPASRI ◽  
Fumihiko IMAMURA
Keyword(s):  
Genetic Algorithm ◽  
Multi Objective Optimization ◽  
Multi Objective
Sign in / Sign up

Export Citation Format

Share Document