• Journal of information and communication convergence engineering
• /
• v.20 no.1
• /
• pp.22-30
• /
• 2022

The reinforcement learning algorithm has proven its potential in solving sequential decision-making problems under uncertainties, such as finding paths to route data packets in wireless sensor networks. With reinforcement learning, the computation of the optimum path requires careful definition of the so-called reward function, which is defined as a linear function that aggregates multiple objective functions into a single objective to compute a numerical value (reward) to be maximized. In a typical defined linear reward function, the multiple objectives to be optimized are integrated in the form of a weighted sum with fixed weighting factors for all learning agents. This study proposes a reinforcement learning -based routing protocol for wireless sensor network, where different learning agents prioritize different objective goals by assigning weighting factors to the aggregated objectives of the reward function. We assign appropriate weighting factors to the objectives in the reward function of a sensor node according to its hop-count distance to the sink node. We expect this approach to enhance the effectiveness of multi-objective reinforcement learning for wireless sensor networks with a balanced trade-off among competing parameters. Furthermore, we propose SDN (Software Defined Networks) architecture with multiple controllers for constant network monitoring to allow learning agents to adapt according to the dynamics of the network conditions. Simulation results show that our proposed scheme enhances the performance of wireless sensor network under varied conditions, such as the node density and traffic intensity, with a good trade-off among competing performance metrics.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2000.04b
• /
• pp.431-438
• /
• 2000

The cost function consists of the weighting functions concerning the structural responses to be controlled and the controller capability. Therefore, the control efficiency depends on the characteristics of the weighting functions. The objective of this paper is the comparative study of the time domain control strategies of LQR and LQG and the frequency domain strategy of H₂ by setting the equivalent weighting functions to the all control strategies. As a result of analysis, LQR strategy is found to be more efficient than other strategies in terms of the response reduction. but the control force is found to be a little highter. As LQG can compensate the limitation of LQR that all state variables should be identified, LQG is more acceptable algorithm than LQR. Furthermore LQG shows a good performance both in the response reduction and the control force. Finally H₂ algorithm is employed to illustrate the importance of weighting filters considering the frequency characteristics of the response and the controller. It Is shown that the H₂ algorithm is found to be the most effective one for the response control with a little control force having a low frequency band.

• Journal of the Ergonomics Society of Korea
• /
• v.32 no.4
• /
• pp.309-319
• /
• 2013

Objective: The aim of this study is to review and summarize human vibration measurement process, and necessity and methods of frequency weightings for human vibration. Background: Prolonged human exposure to hand-arm vibration and whole-body vibration can result in a range of adverse conditions and the development of occupational diseases such as vibration white finger. For preventing these adverse effects, it is important to correctly apply human vibration measurement process. Method: This manuscript was based on the review and summary of mechanical and human vibration relevant texts, academic papers, materials obtained through web surfing. Results: This manuscript summarizes human vibration measurement process described in ISO standards and relevant texts. The sensitivity of the human body to mechanical vibration is known to be dependent on both the frequency and direction of vibration. To take this into account, varying frequency weighting functions have been developed, and RMS frequency-weighted accelerations are used as the most important quantity to evaluate the effects of vibration on health. ISO provided nine frequency weighting functions in the form of curves and tables. Researches on frequency weightings are focused on development and validation of new frequency weightings to truly reflect the relationship between vibration exposure and its adverse effects. Application: This would be useful information for systematically applying human vibration measurement and analysis process, and for selecting appropriate frequency weighting functions.

• 유체기계공업학회:학술대회논문집
• /
• 2003.12a
• /
• pp.397-403
• /
• 2003

In an attempt to solve multiobjective optimization problems, weighted sum method is most widely used for the advantage that a designer can consider the relative significance of each object functions by weight values but it can be highly sensitive to weight vector and occasionally yield a deviated optimum from the relative weighting values designer designated because the multiobjective function has the form of simple sum of the product of the weighting values and the object functions in traditional approach. To search the design solution well agree to the designer's weighting values, we proposed new multiobjective function which is the functional of each normalized objective functions and considered to find the design solution comparing the distance between the characteristic line and the ideal optimum. In this study, proposed multiobjective function was applied to design high efficiency and low noise axial flow fan and the result shows this approach will be effective for the case that the qualify of the design can be highly affected by the designer's subjectiveness represented as weighting values in multiobjective design optimization process.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11a
• /
• pp.334.2-334
• /
• 2002

In conventional model updating using single-objective optimization techniques, imcompatible physical data are compared with each other using weighting factors. There are no general rules fur selecting the weighting factors since they are not directly related with the dynamic behavior of an updated model. So one of the most difficult tasks, in mr)del updating study, is 'balancing among the correlations', i.e. 'trade-off'. (omitted)

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.380-383
• /
• 2003

In this paper, we propose a fuzzy group decision making method for multiple decision maker-multiple objective programming problems to obtain the agreeable solution. In the proposed method, considering the vague nature of human subjective judgement it is assumed that each of multiple decision makers has a fuzzy goal for each of his/her own objective functions. After eliciting the membership functions from the decision makers for their fuzzy goals, total M-Pareto optimal solution concept is defined in membership spaces in order to deal with multiple decision maker-multiple objective programming problems. For generating a candidate of the agreeable solution which is total M-Pareto optimal, the extended weighted minimax problem is formulated and solved for some weighting vector which is specified by the decision makers in their subjective manner, Given the total M-Pareto optimal solution, each of the derision makers must either be satisfied with the current values of the membership functions, or update his/her weighting vector, However, in general, it seems to be very difficult to find the agreeable solution with which all of the decision makers are satisfied perfectly because of the conflicts between their membership functions. In the proposed method, each of the decision makers is requested to estimate the degree of satisfaction for the candidate of the agreeable solution. Using the estimated values or satisfaction of each of the decision makers, the core concept is desnfied, which is a set of undominated candidates. The interactive algorithm is developed to obtain the agreeable solution which satisfies core conditions.

• International Journal of Automotive Technology
• /
• v.8 no.3
• /
• pp.337-342
• /
• 2007

A multi-objective optimization technique was implemented to obtain optimal topologies of the inner reinforcement for a vehicle's hood simultaneously considering the static stiffness of bending and torsion and natural frequency. In addition, a smoothing scheme was used to suppress the checkerboard patterns in the ESO method. Two models with different curvature were chosen in order to investigate the effect of curvature on the static stiffness and natural frequency of the inner reinforcement. A scale factor was employed to properly reflect the effect of each objective function. From several combinations of weighting factors, a Pareto-optimal topology solution was obtained. As the weighting factor for the elastic strain efficiency went from 1 to 0, the optimal topologies transmitted from the optimal topology of a static stiffness problem to that of a natural frequency problem. It was also found that the higher curvature model had a larger static stiffness and natural frequency than the lower curvature model. From the results, it is concluded that the ESO method with a smoothing scheme was effectively applied to topology optimization of the inner reinforcement of a vehicle's hood.

• Journal of Power System Engineering
• /
• v.14 no.3
• /
• pp.33-38
• /
• 2010

Technology of vehicle industry has been developing and it is required a better vehicle performance than before. Therefore, the consumers are asking not only an economic efficiency, functionality, polished design, ride comfort and silence but also a driving stability. The ride comfort, silence and driving stability are influenced by the size of vehicle and various facilities. But the principal factor is a room noise and vibration sensed by a driver and passenger. Thus, the NVH of vehicle has been raised and used as a principal factor for evaluation of vehicle performance. The primary objective of this study is an optimized design of powertrain mounting system. To optimized design was applied MSC.Nastran optimization modules. Results of dynamic analysis for powertrain mounting system was investigated. By theses results, design variables was applied 12 dynamic spring constant. And the weighting factor according to translational displacement and rotational displacement applied 3 cases. The objective function was applied to minimize displacement of powertrain. And the design variable constraint was imposed dynamic spring constant ratio. The constraint of design variable for objective function was imposed bounce displacement for powertrain.

• Structural Engineering and Mechanics
• /
• v.65 no.2
• /
• pp.173-181
• /
• 2018

In this paper, finite element (FE) model updating based on multi-objective optimization with the surrogate model for a steel plate girder bridge is investigated. Conventionally, FE model updating for bridge structures uses single-objective optimization with finite element analysis (FEA). In the case of the conventional method, computational burden occurs considerably because a lot of iteration are performed during the updating process. This issue can be addressed by replacing FEA with the surrogate model. The other problem is that the updating result from single-objective optimization depends on the condition of the weighting factors. Previous studies have used the trial-and-error strategy, genetic algorithm, or user's preference to obtain the most preferred model; but it needs considerable computation cost. In this study, the FE model updating method consisting of the surrogate model and multi-objective optimization, which can construct the Pareto-optimal front through a single run without considering the weighting factors, is proposed to overcome the limitations of the single-objective optimization. To verify the proposed method, the results of the proposed method are compared with those of the single-objective optimization. The comparison shows that the updated model from the multi-objective optimization is superior to the result of single-objective optimization in calculation time as well as the relative errors between the updated model and measurement.

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.11a
• /
• pp.65.1-65.1
• /
• 2010

Thermal performance tests of solar thermal collectors include determination of coefficient parameters in an efficiency equation. The parameters can be estimated using regression method to minimize an objective function as sum of differences between measured efficiency data and regressed efficiency equation. However, this conventional approach doesn't consider measurement uncertainties. In this presentation, a method to determine regression parameters in the efficiency equation and uncertainties of the parameters is described with mainly mathematical expressions based on literature reviews. In the method, parameters in the equation for collector efficiency can be determined using regression analysis with a weighting factor in the objective function. The weighting factor can be uncertainties of the differences between measured and fitted efficiencies. To evaluate the approach, performance estimation of a solar collector using the efficiency equation with uncertainties is compared to the result using the conventional efficiency equation by a simulated way for a case in one of previous studies.