• Tribology and Lubricants
• /
• v.39 no.3
• /
• pp.94-101
• /
• 2023

Automotive wheel bearings are a critical component of vehicles that support their weight and facilitate rotation. Life and stiffness are significant performance characteristics of wheel bearings. Designing wheel bearings involves finding optimal design variables that satisfy both performances. CO₂ emission reduction and fuel efficiency regulations attribute to the recent increase in design requirements for lightweight and compact automotive parts while maintaining performance. However, achieving a design that maintains performance while reducing weight poses challenges, as performance and weight are generally inversely proportional. In this study, we perform design optimization of automotive wheel bearings considering life and stiffness. We develop a program that calculates the basic rated life and modified rated life based on international standards for evaluating the life of wheel bearings. We develop a regression equation using regression analysis to address the time-consuming stiffness analysis during repetitive analysis. We perform ANOVA and main effect analyses to understand the statistical characteristics of the developed regression equation. Furthermore, we verify its reliability by comparing the predicted and test results. We perform design optimization using the developed life prediction program, stiffness regression equation and weight regression equation. We select bearing specifications and geometry as design variables, weight as the cost function, and life and stiffness as constraints. Through design optimization, we investigate the influence of design variables on the cost function and constraints by comparing the initial and optimal design values.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.5
• /
• pp.691-697
• /
• 2010

Reliability-based topology optimization (RBTO) is to get an optimal topology satisfying uncertainties of design variables. In this study, reliability-based topology optimization method is applied to the inner reinforcement of vehicle's hood based on BESO. A multi-objective topology optimization technique was implemented to obtain optimal topology of the inner reinforcement of the hood. considering the static stiffness of bending and torsion as well as natural frequency. Performance measure approach (PMA), which has probabilistic constraints that are formulated in terms of the reliability index, is adopted to evaluate the probabilistic constraints. To evaluate the obtained optimal topology by RBTO, it is compared with that of DTO of the inner reinforcement of the hood. It is found that the more suitable topology is obtained through RBTO than DTO even though the final volume of RBTO is a little bit larger than that of DTO. From the result, multiobjective optimization technique based on the BESO can be applied very effectively in topology optimization for vehicle's hood reinforcement considering the static stiffness of bending and torsion as well as natural frequency.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.1 no.1
• /
• pp.32-39
• /
• 2012

With the aid of genetic algorithm (GA), global optimization with multiple geometry parameters is feasible in the design of switched flux permanent magnet (SFPM) machines. To investigate the advantages of global optimization over individual optimization, which has been used extensively for the design of SFPM machines, a comparison between the two approaches is carried out for the case of fixed copper loss and volume. In the case of individual parameter optimization, the sequence in which the individual parameters are optimized is very important. In the global optimization a better design can always be achieved although the corresponding torque density is found to be only slightly better than that of individually optimized with correct design sequence. By using the obtained global optimization results, the performance in machines having two types of stator and rotor pole combinations, i.e. 12/10 and 12/14, are compared, and it is shown that higher torque is exhibited in the 12/14 SFPM machine. Finally, this paper also demonstrates that global optimization, with the restriction of equal pole width, magnet thickness and slot opening, can maximize the torque density without significantly sacrificing other performance, such as cogging torque and overload capability.

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.940-947
• /
• 2022

Meta-heuristic algorithms have found their place in optimization problems. Henry gas solubility optimization (HGSO) is one of the newest population-based algorithms. This algorithm is inspired by Henry's law of physics. To evaluate the performance of a new algorithm, it must be used in various problems. On the other hand, the optimization of the proportional-integral-derivative (PID) gains for load-following of a nuclear power plant (NPP) is a good challenge to assess the performance of HGSO. Accordingly, the power control of a pressurized water reactor (PWR) is targeted, based on the point kinetics model with six groups of delayed-neutron precursors. In any optimization problem based on meta-heuristic algorithms, an efficient objective function is required. Therefore, the integral of the time-weighted square error (ITSE) performance index is utilized as the objective (cost) function of HGSO, which is constrained by a stability criterion in steady-state operations. A Lyapunov approach guarantees this stability. The results show that this method provides superior results compared to an empirically tuned PID controller with the least error. It also achieves good accuracy compared to an established GA-tuned PID controller.

• Journal of Hydrogen and New Energy
• /
• v.32 no.4
• /
• pp.212-218
• /
• 2021

In this study, we conducted a design optimization of the Type 4 composite pressure vessels to enhance the pressure-resistant performance of the vessels while keeping the thickness of the composite layer. The design variables for the optimization were the stacking angles of the helical layers of the vessels to improve the performance. Since the carbon fibers are expensive material, it is desirable to reduce the use of the carbon fibers by applying an optimal design of the composite pressure vessel. The structural analysis and optimization process for the design of Type 4 composite pressure vessels were carried out using a commercial finite element analysis software, Abaqus and a plug-in for automated simulation, Isight, respectively. The optimization results confirmed the performance and safety of the optimized Type 4 composite pressure vessels was enhanced by 12.84% compared to the initial design.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.5
• /
• pp.637-644
• /
• 2010

This paper presents a reliability-based shape optimization (RBSO) using the growth-strain method. An actual design involves uncertain conditions such as material property, operational load, Poisson's ratio and dimensional variation. The purpose of the RBSO is to consider the variations of probabilistic constraint and performances caused by uncertainties. In this study, the growth-strain method was applied to shape optimization of reliability analysis. Even though many papers for reliability-based shape optimization in mathematical programming method and ESO (Evolutionary Structural Optimization) were published, the paper for the reliability-based shape optimization using the growth-strain method has not been applied yet. Growth-strain method is applied to performance measure approach (PMA), which has probabilistic constraints that are formulated in terms of the reliability index, is adopted to evaluate the probabilistic constraints in the change of average mises stress. Numerical examples are presented to compare the DO with the RBSO. The results of design example show that the RBSO model is more reliable than deterministic optimization. It was verified that the reliability-based shape optimization using growth-strain method are very effective for general structure. The purpose of this study is to improve structure's safety considering probabilistic variable.

• Geomechanics and Engineering
• /
• v.24 no.3
• /
• pp.237-251
• /
• 2021

The main purpose of this study is to investigate the performance of the proposed hybrid teaching-learning based optimization algorithm on the optimum design of reinforced concrete (RC) cantilever retaining walls. For this purpose, three different design examples are optimized with 100 independent runs considering continuous and discrete variables. In order to determine the algorithm performance, the optimization results were compared with the outcomes of the nine powerful meta-heuristic algorithms applied to this problem, previously: the big bang-big crunch (BB-BC), the biogeography based optimization (BBO), the flower pollination (FPA), the grey wolf optimization (GWO), the harmony search (HS), the particle swarm optimization (PSO), the teaching-learning based optimization (TLBO), the jaya (JA), and Rao-3 algorithms. Moreover, Rao-1 and Rao-2 algorithms are applied to this design problem for the first time. The objective function is defined as minimizing the total material and labor costs including concrete, steel, and formwork per unit length of the cantilever retaining walls subjected to the requirements of the American Concrete Institute (ACI 318-05). Furthermore, the effects of peak ground acceleration value on minimum total cost is investigated using various stem height, surcharge loads, and backfill slope angle. Finally, the most robust results were obtained by HTLBO with 50 populations. Consequently the optimization results show that, depending on the increase in PGA value, the optimum cost of RC cantilever retaining walls increases smoothly with the stem height but increases rapidly with the surcharge loads and backfill slope angle.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.769-774
• /
• 2024

The availability of PMT(Project Management Tool) in the market has been increasing rapidly in recent years and Significant advancements have been made for project managers to use for planning, monitoring, and control. Recently, studies applying the Reinforcement-Learning Based Construction Schedule Simulation algorithm for construction project process planning/management are increasing. When reinforcement learning is applied, the agent recognizes the current state and learns to select the action that maximizes the reward among selectable actions. However, if the action of global optimal points is not selected in simulation selection, the local optimal resource may receive continuous compensation (+), which may result in failure to reach the global optimal point. In addition, there is a limitation that the optimization time can be long as numerous iterations are required to reach the global optimal point. Therefore, this study presented a method to improve optimization performance by increasing the probability that a resource with high productivity and low unit cost is selected, preventing local optimization, and reducing the number of iterations required to reach the global optimal point. In the performance evaluation process, we demonstrated that this method leads to closer approximation to the optimal value with fewer iterations.

• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.377-382
• /
• 2007

This paper proposes a training algorithm for global optimization of the parameters of radial basis function networks. Since conventional training algorithms usually perform only local optimization, the performance of the network is limited and the final network significantly depends on the initial network parameters. The proposed hybrid simulated annealing algorithm performs global optimization of the network parameters by combining global search capability of simulated annealing and local optimization capability of gradient-based algorithms. Via experiments for function approximation problems, we demonstrate that the proposed algorithm can find networks showing better training and test performance and reduce effects of the initial network parameters on the final results.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.99-112
• /
• 2010

Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.