Balancing diversity and convergence among solutions in many-objective optimization is challenging, particularly in high-dimensional spaces with conflicting objectives. This paper presents the Many-Objective Marine Predator Algorithm (MaOMPA), an adaptation of the Marine Predators Algorithm (MPA) specifically enhanced for many-objective optimization tasks. MaOMPA integrates an elitist, non-dominated sorting and crowding distance mechanism to maintain a well-distributed set of solutions on the Pareto front. MaOMPA improves upon traditional metaheuristic methods by achieving a robust balance between exploration and exploitation using the predator-prey interaction model. The algorithm underwent evaluation on various benchmarks together with complex real-world engineering problems where it showed superior outcomes when compared against state-of-the-art generational distance and hypervolume and coverage metrics. Engineers and researchers can use MaOMPA as an effective reliable tool to address complex optimization scenarios in engineering design. The MaOMPA source code is available at https://github.com/kanak02/MaOMPA .
- Klíčová slova
- Convergence, Diversity, Information feedback mechanism, Many-objective optimization, Marine predator algorithm, Metaheuristic algorithm,
- MeSH
- algoritmy * MeSH
- potravní řetězec * MeSH
- predátorské chování * MeSH
- zvířata MeSH
- Check Tag
- zvířata MeSH
- Publikační typ
- časopisecké články MeSH
The primary objective of this study is to investigate the microstructural, mechanical, and wear behaviour of AZ31/TiC surface composites fabricated through friction stir processing (FSP). TiC particles are reinforced onto the surface of AZ31 magnesium alloy to enhance its mechanical properties for demanding industrial applications. The FSP technique is employed to achieve a uniform dispersion of TiC particles and grain refinement in the surface composite. Microstructural characterization, mechanical testing (hardness and tensile strength), and wear behaviour evaluation under different operating conditions are performed. Response surface methodology (RSM) is utilized to optimize the wear rate by considering the effects of process parameters. The results reveal a significant improvement in hardness (41.3%) and tensile strength (39.1%) of the FSP-TiC composite compared to the base alloy, attributed to the refined grain structure (6-10 μm) and uniform distribution of TiC particles. The proposed regression model accurately predicts the wear rate, with a confirmation test validating an error percentage within ± 4%. Worn surface analysis elucidates the wear mechanisms, such as shallow grooves, delamination, and oxide layer formation, influenced by the applied load, sliding distance, and sliding velocity. The enhanced mechanical properties and wear resistance are attributed to the synergistic effects of grain refinement, particle-accelerated nucleation, the barrier effect of TiC particles, and improved interfacial bonding achieved through FSP. The optimized FSP-TiC composites exhibit potential for applications in industries demanding high strength, hardness, and wear resistance.
- Klíčová slova
- AZ31 alloy, Friction stir processing, Hardness, Microstructure, Tensile properties, TiC particles, Wear optimization,
- Publikační typ
- časopisecké články MeSH
Many-objective optimization (MaO) is an important aspect of engineering scenarios. In many-objective optimization algorithms (MaOAs), a key challenge is to strike a balance between diversity and convergence. MaOAs employs various tactics to either enhance selection pressure for better convergence and/or implements additional measures for sustaining diversity. With increase in number of objectives, the process becomes more complex, mainly due to challenges in achieving convergence during population selection. This paper introduces a novel Many-Objective Ant Lion Optimizer (MaOALO), featuring the widely-popular ant lion optimizer algorithm. This method utilizes reference point, niche preserve and information feedback mechanism (IFM), to enhance the convergence and diversity of the population. Extensive experimental tests on five real-world (RWMaOP1- RWMaOP5) optimization problems and standard problem classes, including MaF1-MaF15 (for 5, 9 and 15 objectives), DTLZ1-DTLZ7 (for 8 objectives) has been carried out. It is shown that MaOALO is superior compared to ARMOEA, NSGA-III, MaOTLBO, RVEA, MaOABC-TA, DSAE, RL-RVEA and MaOEA-IH algorithms in terms of GD, IGD, SP, SD, HV and RT metrics. The MaOALO source code is available at: https://github.com/kanak02/MaOALO.
- Klíčová slova
- Ant lion optimizer, Convergence, Diversity, MaF benchmark, Many-objective optimization,
- Publikační typ
- časopisecké články MeSH
This research introduces the Multi-Objective Liver Cancer Algorithm (MOLCA), a novel approach inspired by the growth and proliferation patterns of liver tumors. MOLCA emulates the evolutionary tendencies of liver tumors, leveraging their expansion dynamics as a model for solving multi-objective optimization problems in engineering design. The algorithm uniquely combines genetic operators with the Random Opposition-Based Learning (ROBL) strategy, optimizing both local and global search capabilities. Further enhancement is achieved through the integration of elitist non-dominated sorting (NDS), information feedback mechanism (IFM) and Crowding Distance (CD) selection method, which collectively aim to efficiently identify the Pareto optimal front. The performance of MOLCA is rigorously assessed using a comprehensive set of standard multi-objective test benchmarks, including ZDT, DTLZ and various Constraint (CONSTR, TNK, SRN, BNH, OSY and KITA) and real-world engineering design problems like Brushless DC wheel motor, Safety isolating transformer, Helical spring, Two-bar truss and Welded beam. Its efficacy is benchmarked against prominent algorithms such as the non-dominated sorting grey wolf optimizer (NSGWO), multiobjective multi-verse optimization (MOMVO), non-dominated sorting genetic algorithm (NSGA-II), decomposition-based multiobjective evolutionary algorithm (MOEA/D) and multiobjective marine predator algorithm (MOMPA). Quantitative analysis is conducted using GD, IGD, SP, SD, HV and RT metrics to represent convergence and distribution, while qualitative aspects are presented through graphical representations of the Pareto fronts. The MOLCA source code is available at: https://github.com/kanak02/MOLCA.
- Klíčová slova
- Engineering design optimization, Liver cancer algorithm, MOLCA, Multi objective optimization, Non-dominated solution, Pareto front, Pareto solution,
- Publikační typ
- časopisecké články MeSH
The exponential distribution optimizer (EDO) represents a heuristic approach, capitalizing on exponential distribution theory to identify global solutions for complex optimization challenges. This study extends the EDO's applicability by introducing its multi-objective version, the multi-objective EDO (MOEDO), enhanced with elite non-dominated sorting and crowding distance mechanisms. An information feedback mechanism (IFM) is integrated into MOEDO, aiming to balance exploration and exploitation, thus improving convergence and mitigating the stagnation in local optima, a notable limitation in traditional approaches. Our research demonstrates MOEDO's superiority over renowned algorithms such as MOMPA, NSGA-II, MOAOA, MOEA/D and MOGNDO. This is evident in 72.58% of test scenarios, utilizing performance metrics like GD, IGD, HV, SP, SD and RT across benchmark test collections (DTLZ, ZDT and various constraint problems) and five real-world engineering design challenges. The Wilcoxon Rank Sum Test (WRST) further confirms MOEDO as a competitive multi-objective optimization algorithm, particularly in scenarios where existing methods struggle with balancing diversity and convergence efficiency. MOEDO's robust performance, even in complex real-world applications, underscores its potential as an innovative solution in the optimization domain. The MOEDO source code is available at: https://github.com/kanak02/MOEDO .
- Publikační typ
- časopisecké články MeSH
An experimental study of three body abrasive wear behaviour of AZ31/15 vol.% Zirconium dioxide (ZrO2) reinforced composites prepared by stir casting has been carried out. Microstructural analysis of the developed composites was carried out and found out that the microstructure of the composites revealed a uniform distribution of ZrO2 particles with refinement in the grain size of the matrix from 70 to 20 µm. The alterations in the microstructure led to an enhancement in both hardness (68-104 HV) and tensile strength (156-236 MPa) due to Orowan strengthening, quench hardening effect and better bonding. Response surface methodology was applied to formulate the three-body abrasive wear test characteristics such as load, speed, and time. Three body abrasive test results were utilized to generate surface graphs for different combinations of wear test parameters revealed an increase in specific wear rate. The specific wear rate was observed to increase with increase in speed up to a certain level and then started to decrease. The lowest possible specific wear rate was obtained for an optimized load of 20 N and a speed of 190 ms-1. Scanning electron microscopic examination of wear-tested samples showed higher specific wear rate at higher loads with predominantly abrasion type material removal. In conclusion, this study makes a substantial contribution to the field by elucidating the complex relationships among microstructure, mechanical properties, and the three-body abrasive wear behavior of AZ31/ZrO2 composites. The determination of optimal wear conditions and the insights gained into wear mechanisms provide valuable information for designing materials, implementing engineering solutions, and advancing the creation of wear-resistant components across a range of industries.
- Publikační typ
- časopisecké články MeSH
Feature selection is a critical component of machine learning and data mining which addresses challenges like irrelevance, noise, redundancy in large-scale data etc., which often result in the curse of dimensionality. This study employs a K-nearest neighbour wrapper to implement feature selection using six nature-inspired algorithms, derived from human behaviour and mammal-inspired techniques. Evaluated on six real-world datasets, the study aims to compare the performance of these algorithms in terms of accuracy, feature count, fitness, convergence and computational cost. The findings underscore the efficacy of the Human Learning Optimization, Poor and Rich Optimization and Grey Wolf Optimizer algorithms across multiple performance metrics. For instance, for mean fitness, Human Learning Optimization outperforms the others, followed by Poor and Rich Optimization and Harmony Search. The study suggests the potential of human-inspired algorithms, particularly Poor and Rich Optimization, in robust feature selection without compromising classification accuracy.
- Klíčová slova
- Algorithms, Feature reduction, KNN, Metaheuristics, Non-traditional algorithms, Optimization,
- Publikační typ
- časopisecké články MeSH
Dry sliding wear behaviour of friction stir processed (FSP) AZ31 and AZ31/ZrC particles (5, 10, and 15 vol%) reinforced surface composite was investigated at different sliding speeds and loads. The samples were tested using a pin-on-disc apparatus with EN31 steel as the counter body to determine the role of FSP and ZrC reinforcement on the microstructure, hardness, and wear behaviour of AZ31. Base metal AZ31 alloy exhibits a hardness of 60 HV, whereas the 15 vol% ZrC-reinforced composites had the highest hardness of 108 HV. It was also identified that 15 vol% ZrC-reinforced composites exhibited lowest wear rate and friction coefficient under all testing conditions. Abrasion, delamination, oxidation, material softening, and plastic deformation are the primary wear mechanisms viewed from the wear tracks of the samples. Higher volume fraction of ZrC particles exhibited better wear resistance at all speeds and loads than AZ31 alloy. A wear map has been generated for different material compositions and wear conditions to identify the main wear mechanisms easily.
- Publikační typ
- časopisecké články MeSH
