Browsing by Author "Pholdee, Nantiwat"

Now showing 1 - 20 of 23

A comparative study of state-of-the-art metaheuristics for solving many-objective optimization problems of fixed wing unmanned aerial vehicle conceptual design
(Springer, 2023-04-11) Anosri, Siwakorn; Panagant, Natee; Champasak, Pakin; Bureerat, Sujin; Thipyopas, Chinnapat; Kumar, Sumit; Pholdee, Nantiwat; Yıldız, Betül Sultan; Yıldız, Ali Riza; YILDIZ, ALİ RIZA; YILDIZ, BETÜL SULTAN; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü.; 0000-0001-7592-8733 ; AAH-6495-2019; F-7426-2011
The complexity of aircraft design problems increases with many objectives and diverse constraints, thus necessitating effective optimization techniques. In recent years many new metaheuristics have been developed, but their implementation in the design of the aircraft is limited. In this study, the effectiveness of twelve new algorithms for solving unmanned aerial vehicle design issues is compared. The optimizers included Differential evolution for multi-objective optimization, Many-objective nondominated sorting genetic algorithm, Knee point-driven evolutionary algorithm for many-objective optimization, Reference vector guided evolutionary algorithm, Multi-objective bat algorithm with nondominated sorting, multi-objective flower pollination algorithm, Multi-objective cuckoo search algorithm, Multi-objective multi-verse optimizer, Multi-objective slime mould algorithm, Multi-objective jellyfish search algorithm, Multi-objective evolutionary algorithm based on decomposition and Self-adaptive many-objective meta-heuristic based on decomposition. The design problems include four many-objective conceptual designs of UAV viz. Conventional, Conventional with winglet, Twin boom and Canard, which are solved by all the optimizers employed. Widely used Hypervolume and Inverted Generational Distance metrics are considered to evaluate and compare the performance of examined algorithms. Friedman's rank test based statistical examination manifests the dominance of the DEMO optimization technique over other compared techniques and exhibits its effectiveness in solving aircraft conceptual design problems. The findings of this work assist in not only solving aircraft design problems but also facilitating the development of unique algorithms for such challenging issues.
A nelder mead-infused info algorithm for optimization of mechanical design problems
(Walter De Gruyter Gmbh, 2022-08-26) Mehta, Pranav; Yıldız, Betül S.; Kumar, Sumit; Pholdee, Nantiwat; Sait, Sadiq M.; Panagant, Natee; Bureerat, Sujin; Yıldız, Ali Rıza; YILDIZ, BETÜL SULTAN; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü.; AAL-9234-2020; F-7426-2011
Nature-inspired metaheuristic algorithms have wide applications that have greater emphasis over the classical optimization techniques. The INFO algorithm is developed on the basis of the weighted mean of the vectors, which enhances the superior vector position that enables to get the global optimal solution. Moreover, it evaluates the fitness function within the updating stage, vectors combining, and local search stage. Accordingly, in the present article, a population-based algorithm named weighted mean of vectors (INFO) is hybridized with the Nelder-Mead algorithm (HINFO-NM) and adapted to optimize the standard benchmark function structural optimization of the vehicle suspension arm. This provides a superior convergence rate, prevention of trapping in the local search domain, and class balance between the exploration and exploitation phase. The pursued results suggest that the HINFO-NM algorithm is the robust optimizer that provides the best results compared to the rest of the algorithms. Moreover, the scalability of this algorithm can be realized by having the least standard deviation in the results. The HINFO-NM algorithm can be adopted in a wide range of optimization challenges by assuring superior results obtained in the present article.
A new chaotic levy flight distribution optimization algorithm for solving constrained engineering problems
(Wiley, 2022-03-23) Kumar, Sumit; Pholdee, Nantiwat; Bureerat, Sujin; Sait, Sadiq M.; YILDIZ, ALİ RIZA; YILDIZ, BETÜL SULTAN; 0000-0002-7493-2068; 0000-0003-1790-6987; AAL-9234-2020; F-7426-2011
This work proposed a new metaheuristic dubbed as Chaotic Levy flight distribution (CLFD) algorithm, to address physical world engineering optimization problems that incorporate the chaotic maps in the elementary Levy flight distribution (LFD). Hybridization aims to increase the LFD rate of convergence while also providing a problem-free optimization approach. The proposed methodology is investigated for five case studies of constrained optimization issues followed by shape optimization of structural design. The outcomes from the CFLD algorithm are further contrasted with its fundamental version and other distinguished recently introduced algorithms. The computational analysis illustrates the dominance of CLFD over other considered optimizers. Moreover, the present investigation shows that CLFD is a robust technique that can efficiently find optimal mechanical design problems with a proper chaotic map selection.
A novel generalized normal distribution optimizer with elite oppositional based learning for optimization of mechanical engineering problems
(Gmbh, 2023-02-23) Mehta, Pranav; Yıldız, Betuel Sultan; Pholdee, Nantiwat; Kumar, Sumit; Riza Yıldız, Ali; Sait, Sadiq M. M.; Bureerat, Sujin; YILDIZ, BETÜL SULTAN; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü; F-7426-2011; AAH-6495-2019
Optimization of engineering discipline problems are quite a challenging task as they carry design parameters and various constraints. Metaheuristic algorithms can able to handle those complex problems and realize the global optimum solution for engineering problems. In this article, a novel generalized normal distribution algorithm that is integrated with elite oppositional-based learning (HGNDO-EOBL) is studied and employed to optimize the design of the eight benchmark engineering functions. Moreover, the statistical results obtained from the HGNDO-EOBL are collated with the data obtained from the well-established algorithms such as whale optimizer, salp swarm optimizer, LFD optimizer, manta ray foraging optimization algorithm, hunger games search algorithm, reptile search algorithm, and INFO algorithm. For each of the cases, a comparison of the statistical results suggests that HGNDO-EOBL is superior in terms of realizing the prominent values of the fitness function compared to established algorithms. Accordingly, the HGNDO-EOBL can be adopted for a wide range of engineering optimization problems.
A novel hybrid flow direction optimizer-dynamic oppositional based learning algorithm for solving complex constrained mechanical design problems
(Walter de Gruyter Gmbh, 2023-01-27) Yıldız, Betül Sultan; Pholdee, Nantiwat; Mehta, Pranav; Sait, Sadiq M.; Kumar, Sumit; Bureerat, Sujin; Yıldız, Ali Rıza; YILDIZ, BETÜL SULTAN; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Makine Mühendisliği Bölümü; AAL-9234-2020; F-7426-2011
In this present work, mechanical engineering optimization problems are solved by employing a novel optimizer (HFDO-DOBL) based on a physics-based flow direction optimizer (FDO) and dynamic oppositional-based learning. Five real-world engineering problems, viz. planetary gear train, hydrostatic thrust bearing, robot gripper, rolling bearing, and multiple disc clutch brake, are considered. The computational results obtained by HFDO-DOBL are compared with several newly proposed algorithms. The statistical analysis demonstrates the HFDO-DOBL dominance in finding optimal solutions relatively and competitiveness in solving constraint design optimization problems.
A novel hybrid marine predators-Nelder-Mead optimization algorithm for the optimal design of engineering problems
(Walter, 2021-01-01) Panagant, Natee; Yıldız, Mustafa; Pholdee, Nantiwat; Yıldız, Ali Riza; Bureerat, Sujin; Sait, Sadiq M.; YILDIZ, ALİ RIZA; Yıldız, Mustafa; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü; JTZ-2884-2023; F-7426-2011
The marine predators optimization algorithm (MPA) is a recently developed nature-inspired algorithm. In this paper, the Nelder-Mead algorithm is utilized to improve the local exploitation powers of the MPA when described as a hybrid marine predators and Nelder-Mead (HMPANM). Due to the harsh competitive conditions as well as the transition to new vehicles such as hybrid and full-electrical cars, the interest in the design of light and low-cost vehicles is increasing. In this study, a recent metaheuristic addition, a hybrid marine predators optimization algorithm, is used to solve a structural design optimization problem to prove how the HMPANM can be used in solving industrial design problems. The results strongly prove the capability of the HMPANM for the optimum design of components in the automotive industry.
A small fixed-wing UAV system identification using metaheuristics
(Taylor & Francis As, 2022-12-31) Nonut, Apiwat; Kanokmedhakul, Yodsadej; Bureerat, Sujin; Kumar, Sumit; Tejani, Ghanshyam G.; Artrit, Pramin; Yıldız, Ali Rıza; Pholdee, Nantiwat; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü.; F-7426-2011
A novel method for system identification of small-scale fixed-wing Unmanned Aerial Vehicles (UAVs) using a metaheuristics (MHs) approach is proposed. This investigation splits the complex aerodynamic model of UAV into longitudinal and lateral dynamics sub-systems. The system identification optimisation problem is proposed to find the UAV aerodynamic and stability derivatives by minimizing the R-squared error between the measurement data and the flight dynamic model. Thirteen popular optimisation algorithms are applied for solving the proposed UAV system identification optimisation problem while each algorithm is tested for 10 independent optimisation runs. By performing the Freidman's rank test, statistical analysis of the experiment work was carried out while, based on the fitness value, each algorithm is ranked. The outcomes demonstrate the dominance of the L-SHADE algorithm, with mean R-square errors of 0.5465 and 0.0487 for longitudinal and lateral dynamics, respectively. It is considered superior to the other algorithms for this system identification problem.
Aircraft control parameter estimation using self-adaptive teaching-learning-based optimization with an acceptance probability
(Hindawi, 2021-12-01) Kanokmedhakul, Yodsadej; Panagant, Natee; Bureerat, Sujin; Pholdee, Nantiwat; Yıldız, Ali Rıza; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü.; 0000-0003-1790-6987; F-7426-2011
This work presents a metaheuristic (MH) termed, self-adaptive teaching-learning-based optimization, with an acceptance probability for aircraft parameter estimation. An inverse optimization problem is presented for aircraft longitudinal parameter estimation. The problem is posed to find longitudinal aerodynamic parameters by minimising errors between real flight data and those calculated from the dynamic equations. The HANSA-3 aircraft is used for numerical validation. Several established MHs along with the proposed algorithm are used to solve the proposed optimization problem, while their search performance is investigated compared to a conventional output error method (OEM). The results show that the proposed algorithm is the best performer in terms of search convergence and consistency. This work is said to be the baseline for purely applying MHs for aircraft parameter estimation.
Airfoil shape optimisation using a multi-fidelity surrogate-assisted metaheuristic with a new multi-objective infill sampling technique
(Tech Science Press, 2023-06-30) Aye, Cho Mar; Wansaseub, Kittinan; Kumar, Sumit; Tejani, Ghanshyam G.; Bureerat, Sujin; Pholdee, Nantiwat; Yıldız, Ali Rıza; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi.; F-7426-2011
This work presents multi-fidelity multi-objective infill-sampling surrogate-assisted optimization for airfoil shape optimization. The optimization problem is posed to maximize the lift and drag coefficient ratio subject to airfoil geometry constraints. Computational Fluid Dynamic (CFD) and XFoil tools are used for high and low-fidelity simulations of the airfoil to find the real objective function value. A special multi-objective sub-optimization problem is proposed for multiple points infill sampling exploration to improve the surrogate model constructed. To validate and further assess the proposed methods, a conventional surrogate-assisted optimization method and an infill sampling surrogate-assisted optimization criterion are applied with multi-fidelity simulation, while their numerical performance is investigated. The results obtained show that the proposed technique is the best performer for the demonstrated airfoil shape optimization. According to this study, applying multi-fidelity with multi-objective infill sampling criteria for surrogate-assisted optimization is a powerful design tool.
Automated design of aircraft fuselage stiffeners using multiobjective evolutionary optimisation
(Inderscience Enterprises, 2020-09-22) Sarangkum, Ruangrit; Wansasueb, Kittinan; Panagant, Natee; Pholdee, Nantiwat; Bureerat, Sujin; Sait, Sadiq M; Yıldız, Ali Rıza; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği Bölümü.; F-7426-2011; 7102365439
This paper proposes an optimisation process for the design of aircraft fuselage stiffeners using evolutionary optimisation. A new design problem is developed to find a layout for fuselage stiffeners (rings and stringers) such that the structural mass, compliance, and the first-mode natural frequency can be optimised, subject to structural constraints. The stiffeners are modelled as beam elements. Three multiobjective meta-heuristics are employed to solve the problem, and a comparative study of the results of these optimisers is carried out. It is found that the proposed layout synthesis problem for aircraft fuselage stiffeners leads to a set of efficient structural solutions, which can be used at the decision-making stage. It is an automated design strategy with high potential for further investigation.
Comparative performance of twelve metaheuristics for wind farm layout optimisation
(Springer, 2022-01) Kunakote, Tawatchai; Sabangban, Numchoak; Tejani, Ghanshyam G.; Panagant, Natee; Pholdee, Nantiwat; Kumar, Sumit; Yıldız, Ali Rıza; Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği; 0000-0003-1790-6987; F-7426-2011; 7102365439
This work bridges two research fields i.e. metaheuristics and wind farm layout design. Comparative performance of twelve metaheuristics (MHs) on wind farm layout optimisation (WFLO) was conducted. Four WFLO problems are proposed for benchmarking the various metaheuristics while the design problem is an attempt to simultaneously minimise wind farm cost and maximise wind farm totally produced power. Design variables are wind turbine placement with fixed and varied number of wind turbines. The Jansen's wake model is used while two types of energy estimation with and without considering partially overshadowed wake areas are studied. The results obtained from using various MHs are statistically compared in terms of convergence and consistency while the best performer is obtained. Comparison results indicated that moth-flame optimisation (MFO) algorithm is the most efficient algorithms. The results obtained in this work are said to be the baseline for future study on WFLO using metahueristics.
A comparative study of recent multi-objective metaheuristics for solving constrained truss optimisation problems
(Springer, 2021-08) Panagant, Natee; Pholdee, Nantiwat; Bureerat, Sujin; Mirjalili, Seyedali; Yıldız, Ali Rıza; Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği.; 0000-0003-1790-6987; F-7426-2011; 7102365439
Multi-objective truss optimisation is a research topic that has been less investigated in the literature compared to the single-objective cases. This paper investigates the comparative performance of fourteen new and established multi-objective metaheuristics when solving truss optimisation problems. The optimisers include multi-objective ant lion optimiser, multi-objective dragonfly algorithm, multi-objective grasshopper optimisation algorithm, multi-objective grey wolf optimiser, multi-objective multi-verse optimisation, multi-objective water cycle algorithm, multi-objective Salp swarm algorithm, success history-based adaptive multi-objective differential evolution, success history-based adaptive multi-objective differential evolution with whale optimisation, non-dominated sorting genetic algorithm II, hybridisation of real-code population-based incremental learning and differential evolution, differential evolution for multi-objective optimisation, multi-objective evolutionary algorithm based on decomposition, and unrestricted population size evolutionary multi-objective optimisation algorithm. The design problem is assigned to minimise structural mass and compliance subject to stress constraints. Eight classical trusses found in the literature are used for setting up the design test problems. Various optimisers are then implemented to tackle the problems. A comprehensive comparative study is given to critically analyse the performance of all algorithms in this problem area. The results provide new insights to the pros and cons of evolutionary multi-objective optimisation algorithms when addressing multiple, often conflicting objective in truss optimisation. The results and findings of this work assist with not only solving truss optimisation problem better but also designing customised algorithms for such problems.
Comparision of the political optimization algorithm, the Archimedes optimization algorithm and the Levy flight algorithm for design optimization in industry
(Walter De Gruyter GMBH, 2021-04) Pholdee, Nantiwat; Bureerat, Sujin; Kaen, Khon; Sait, Sadiq M.; Yıldız, Betül Sultan; Erdaş, Mehmet Umut; Yıldız, Ali Rıza; Uludağ Üniversitesi/Mühendislik Fakültesi/Otomotiv Mühendisliği.; Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği.; AAL-9234-2020; F-7426-2011; CNV-1200-2022; 57094682600; 57298176600; 7102365439
This article focuses on minimizing product costs by using the newly developed political optimization algorithm (POA), the Archimedes 'optimization algorithm (AOA), and the Levy flight algorithm (LFA) in product development processes. Three structural optimization methods, size optimization, shape optimization, and topology optimization, are extensively applied to create inexpensive structures and render designs efficient. Using size, shape, and topology optimization in an integrated way, It is possible to obtain the most efficient structures in industry. The political optimization algorithm (POA) is a metaheuristic algorithm that can be used to solve many optimization problems. This study investigates the search capability and computational efficiency of POA for optimizing vehicle structures. By examining the results obtained, we prove the apparent superiority of the POA to other recent famous metaheuristics such as the Archimedes optimization algorithm and the Levy flight algorithm. The most important result of this paperwill be to provide an impressive aid for industrial companies to fill the gaps in their product design stages.
Comparison of recent algorithms for many-objective optimisation of an automotive floor-frame
(Inderscience Enterprises, 2019) Panagant, Natee; Pholdee, Nantiwat; Wansasueb, Kittinan; Bureerat, Sujin; Sait, Sadiq M.; Yıldız, Ali Rıza; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği/Konstrüksiyon ve İmalat Bölümü.; F-7426-2011; 7102365439
In this paper, an approach called real-code population-based incremental learning hybridised with adaptive differential evolution (RPBILADE) is proposed for solving many-objective automotive floor-frame optimisation problems. Adaptive strategies are developed and integrated into the algorithm. The purpose of these strategies is to select suitable control parameters for each stage of an optimisation run, in order to improve the search performance and consistency of the algorithm. The automotive floor-frame structures are considered as frame structures that can be analysed with finite element analysis. The design variables of the problems include topology, shape, and size. Ten optimisation runs using various optimisers are carried out on two many-objective automotive floor-frame optimisation problems. Twelve additional benchmark tests against all competitors are also performed to demonstrate the search performance of the proposed algorithm. RPBILADE provided better results than other recent optimisers for both the automotive floor-frame optimisation and benchmark problems.
Conceptual comparison of the ecogeography-based algorithm, equilibrium algorithm, marine predators algorithm and slime mold algorithm for optimal product design
(Walter De Gruyter GMBH, 2021-07-01) Patel, Vivek; Pholdee, Nantiwat; Sait, Sadiq M.; Bureerat, Sujin; Yıldız, Betül Sultan; Yıldız, Ali Rıza; Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği.; 0000-0003-1790-6987; 0000-0002-7493-2068; AAL-9234-2020; F-7426-2011; 57094682600; 7102365439
Vehicle component design is crucial for developing a vehicle prototype, as optimum parts can lead to cost reduction and performance enhancement of the vehicle system. The use of metaheuristics for vehicle component optimization has been commonplace due to several advantages: robustness and simplicity. This paper aims to demonstrate the shape design of a vehicle bracket by using a newly invented metaheuristic. The new optimizer is termed the ecogeography-based optimization algorithm (EBO). This is arguably the first vehicle design application of the new optimizer. The optimization problem is posed while EBO is implemented to solve the problem. It is found that the design results obtained from EBO are better when compared to other optimizers such as the equilibrium optimization algorithm, marine predators algorithm, slime mold algorithm.
Hybrid spotted hyena-Nelder-Mead optimization algorithm for selection of optimal machining parameters in grinding operations
(Walter De Gruyter Gmbh, 2021-01-01) Pholdee, Nantiwat; Patel, Vivek K.; Sait, Sadiq M.; Bureerat, Sujin; Yıldız, Ali Rıza; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Otomotiv Mühendisliği Bölümü.; F-7426-2011
In this research, a novel optimization algorithm, which is a hybrid spotted hyena-Nelder-Mead optimization algorithm (HSHO-NM) algorithm, has been introduced in solving grinding optimization problems. A well-known grinding optimization problem is solved to prove the superiority of the HSHO-NM over other algorithms. The results of the HSHO-NM are compared with others. The results show that HSHO-NM is an efficient optimization approach for obtaining the optimal manufacturing variables in grinding operations.
Hybrid taguchi-levy flight dis-tribution optimization algorithm for solving real-world design optimization problems
(Walter, 2021-06-01) Yıldız, Mustafa; Panagant, Natee; Pholdee, Nantiwat; Bureerat, Sujin; Sait, Sadiq M.; Yıldız, Ali Rıza; Yıldız, Mustafa; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Otomotiv Mühendisliği Bölümü; F-7426-2011; JTZ-2884-2023
The Levy flight distribution optimization algorithm is a recently developed meta-heuristic. In this study, the Levy flight distribution optimization algorithm and the Taguchi method are hybridized to solve the shape optimization problem, which is the final step in developing optimum structural components. The new method is termed the hybrid Levy flight distribution and Taguchi (HLFD-T) algorithm. Geometric dimensions are used as design variables in the optimization, and the problem is aimed at mass minimization. The constraint in the problem is the maximum stress value. The well-known Kriging meta-modeling approach and a specifically developed hybrid approach have been coupled in this paper to find the component's optimal geometry. The results show that the proposed hybrid algorithm (HLFD-T) has more robust features than the ant lion algorithm, the whale algorithm, and the Levy flight distribution optimization algorithm for obtaining an optimal component geometry.
Hybridised differential evolution and equilibrium optimiser with learning parameters for mechanical and aircraft wing design
(Elsevier, 2022-01-10) Wansasueb, Kittinan; Panmanee, Sorasak; Panagant, Natee; Pholdee, Nantiwat; Bureerat, Sujin; Yıldız, Ali Rıza; YILDIZ, ALİ RIZA; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği Bölümü.; F-7426-2011
Metaheuristics (MHs) have been widely used for aeroelastic optimisation of aircraft wings and other types of aircraft structures. Using such methods offers some advantages e.g. flexibility for coding, robustness, global optimisation capability, and a derivative-free feature. Moreover, unconventional design problems can be posed when using metaheuristics. This paper proposes a new hybrid algorithm, named HDEEO-LP, with a learning control parameter for aeroelastic optimisation. The new optimiser is obtained from hybridising differential evolution and the recently invented equilibrium optimisation, while a learning scheme for control parameter tuning is integrated. The new method is tested against a number of established and recently invented MHs, such as a grey wolf optimiser (GWO), a salp swarm algorithm (SSA), an equilibrium optimiser (EO), an artificial bee colony (ABC), teaching-learning based optimisation (TLBO), water cycle algorithm (WCA), self-adaptive spherical search algorithm (SASS) using the CEC-RW-2020 test suite and the Goland wing aeroelastic optimisation. The results reveal that the proposed hybrid algorithm is among the top performers.
Multi-surrogate-assisted metaheuristics for crashworthiness optimisation
(Inderscience, 2019) Aye, Cho Mar; Pholdee, Nantiwat; Bureerat, Sujin; Sait, Sadiq M.; Yıldız, Ali Rıza; Bursa Uludağ Üniversitesi/Mühendislik Fakültesi/Makine Mühendisliği Bölümü.; F-7426-2011; 7102365439
This work proposes a multi-surrogate-assisted optimisation and performance investigation of several newly developed metaheuristics (MHs) for the optimisation of vehicle crashworthiness. The optimisation problem for car crashworthiness is posed to find the shape and size of a crash box while the objective function is to maximise the total energy absorption subject to a mass constraint. Two main numerical experiments are conducted. Firstly, the performance of different surrogate models along with the proposed multi-surrogate model is investigated. Secondly, several MHs are applied to tackle the proposed crashworthiness optimisation problem by employing the best obtained surrogate model. The results reveal that the proposed multi-surrogate model is the best performer. Among the several MHs used in this study, sine cosine algorithm is the best algorithm for the proposed multi-surrogate model. Based on this study, the application of the proposed multi-surrogate model is better than using one particular traditional surrogate model, especially for constrained optimisation.
A novel chaotic Henry gas solubility optimization algorithm for solving real-world engineering problems
(Springer, 2022-06) Pholdee, Nantiwat; Panagant, Natee; Bureerat, Sujin; Sait, Sadiq M.; Yıldız, Betül Sultan; Yıldız, Ali Rıza; Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği.; Uludağ Üniversitesi/Mühendislik Fakültesi/Makina Mühendisliği.; 0000-0002-7493-2068; 0000-0003-1790-6987; AAL-9234-2020; F-7426-2011; 57094682600; 7102365439
The paper proposes a novel metaheuristic based on integrating chaotic maps into a Henry gas solubility optimization algorithm (HGSO). The new algorithm is named chaotic Henry gas solubility optimization (CHGSO). The hybridization is aimed at enhancement of the convergence rate of the original Henry gas solubility optimizer for solving real-life engineering optimization problems. This hybridization provides a problem-independent optimization algorithm. The CHGSO performance is evaluated using various conventional constrained optimization problems, e.g., a welded beam problem and a cantilever beam problem. The performance of the CHGSO is investigated using both the manufacturing and diaphragm spring design problems taken from the automotive industry. The results obtained from using CHGSO for solving the various constrained test problems are compared with a number of established and newly invented metaheuristics, including an artificial bee colony algorithm, an ant colony algorithm, a cuckoo search algorithm, a salp swarm optimization algorithm, a grasshopper optimization algorithm, a mine blast algorithm, an ant lion optimizer, a gravitational search algorithm, a multi-verse optimizer, a Harris hawks optimization algorithm, and the original Henry gas solubility optimization algorithm. The results indicate that with selecting an appropriate chaotic map, the CHGSO is a robust optimization approach for obtaining the optimal variables in mechanical design and manufacturing optimization problems.