• Geomechanics and Engineering
• /
• v.39 no.1
• /
• pp.27-41
• /
• 2024

Accurately estimating the performance of tunnel boring machines (TBMs) is crucial for mitigating the substantial financial risks and complexities associated with tunnel construction. Machine learning (ML) techniques have emerged as powerful tools for predicting non-linear time series data. In this research, six advanced meta-heuristic optimization algorithms based on long short-term memory (LSTM) networks were developed to predict TBM penetration rate (TBM-PR). The study utilized 1125 datasets, partitioned into 20% for testing, 70% for training, and 10% for validation, incorporating six key input parameters influencing TBM-PR. The performances of these LSTM-based models were rigorously compared using a suite of statistical evaluation metrics. The results underscored the profound impact of optimization algorithms on prediction accuracy. Among the models tested, the LSTM optimized by the particle swarm optimization (PSO) algorithm emerged as the most robust predictor of TBM-PR. Sensitivity analysis further revealed that the orientation of discontinuities, specifically the alpha angle (α), exerted the greatest influence on the model's predictions. This research is significant in that it addresses critical concerns of TBM manufacturers and operators, offering a reliable predictive tool adaptable to varying geological conditions.

• Journal of Hydrogen and New Energy
• /
• v.24 no.1
• /
• pp.50-60
• /
• 2013

High temperature proton exchange membrane fuel cells (PEMFCs) using phosphoric acid (PA) doped polybenzimidazole (PBI) membranes have been concentrated as one of solutions to the limits with traditional low temperature PEMFCs. However, the amount of reported experimental data is not enough to catch the operational characteristics correlated with cell performance and durability. In this study, design of experiments (DOE) based operational optimization method for high temperature PEMFCs has been proposed. Response surface method (RSM) is very useful to effectively analyze target system's characteristics and to optimize operating conditions for a short time. Thus RSM using central composite design (CCD) as one of methodologies for design of experiments (DOE) was adopted. For this work, the statistic models which predict the performance and degradation rate with respect to the operating conditions have been developed. The developed performance and degradation models exhibit a good agreement with experimental data. Compared to the existing arbitrary operation, the expected cell lifetime and average cell performance during whole operation could be improved by optimizing operating conditions. Furthermore, the proposed optimization method could find different new optimal solutions for operating conditions if the target lifetime of the fuel cell system is changed. It is expected that the proposed method is very useful to find optimal operating conditions and enhance performance and durability for many other types of fuel cell systems.

• Journal of Korean Society for Quality Management
• /
• v.47 no.4
• /
• pp.701-711
• /
• 2019

Purpose: The problem of optimizing redundancy allocation in multi-level systems is considered when each item in a multi-level system has alternative items with the same function. The number of redundancy of multi-level system is allocated to maximize the reliability of the system under path set and cost limitation constraints. Methods: Based on cost limitation and path set constraints, a mathematical model is established to maximize system reliability. Particle swarm optimization is employed for redundant allocation and verified by numerical experiments. Results: Comparing the particle swarm optimization method and the memetic algorithm for the 3 and 4 level systems, the particle swarm optimization method showed better performance for solution quality and search time. Particularly, the particle swarm optimization showed much less than the memetic algorithm for variation of results. Conclusion: The proposed particle swarm optimization considerably shortens the time to search for a feasible solution in MRAP with path set constraints. PS optimization is expected to reduce search time and propose the better solution for various problems related to MRAP.

• Structural Engineering and Mechanics
• /
• v.72 no.2
• /
• pp.181-190
• /
• 2019

Topology optimization of structures seeking the best distribution of mass in a design space to improve the structural performance and reduce the weight of a structure is one of the most comprehensive issues in the field of structural optimization. In addition to structures stiffness as the most common objective function, frequency optimization is of great importance in variety of applications too. In this paper, an efficient multi-objective Bi-directional Evolutionary Structural Optimization (BESO) method is developed for topology optimization of frequency and stiffness in continuum structures simultaneously. A software package including a Matlab code and Abaqus FE solver has been created for the numerical implementation of multi-objective BESO utilizing the weighted function method. At the same time, by considering the weaknesses of the optimized structure in single-objective optimizations for stiffness or frequency problems, slight modifications have been done on the numerical algorithm of developed multi-objective BESO in order to overcome challenges due to artificial localized modes, checker boarding and geometrical symmetry constraint during the progressive iterations of optimization. Numerical results show that the proposed Multiobjective BESO method is efficient and optimal solutions can be obtained for continuum structures based on an existent finite element model of the structures.

• Structural Engineering and Mechanics
• /
• v.81 no.3
• /
• pp.267-280
• /
• 2022

Multiscale structure has attracted significant interest due to its high stiffness/strength to weight ratios and multifunctional performance. However, most of the existing concurrent topology optimization works are carried out under deterministic load conditions. Hence, this paper proposes a robust concurrent topology optimization method based on the bidirectional evolutionary structural optimization (BESO) method for the design of structures composed of periodic microstructures subjected to uncertain dynamic loads. The robust objective function is defined as the weighted sum of the mean and standard deviation of the module of dynamic structural compliance with constraints are imposed to both macro- and microscale structure volume fractions. The polynomial chaos expansion (PCE) method is used to quantify and propagate load uncertainty to evaluate the objective function. The effective properties of microstructure is evaluated by the numerical homogenization method. To release the computation burden, the decoupled sensitivity analysis method is proposed for microscale design variables. The proposed method is a non-intrusive method, and it can be conveniently extended to many topology optimization problems with other distributions. Several numerical examples are used to validate the effectiveness of the proposed robust concurrent topology optimization method.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.6
• /
• pp.628-641
• /
• 2014

Stepwise efficiency improvement in data envelopment analysis (DEA)-based benchmarking is a realistic and effective method by which inefficient decision making units (DMUs) can choose benchmarks in a stepwise manner and, thereby, effect gradual performance improvement. Most of the previous research relevant to stepwise efficiency improvement has focused primarily on how to stratify DMUs into multiple layers and how to select immediate benchmark targets in leading levels for lagging-level DMUs. It can be said that the sequence of benchmark targets was constructed in a myopic way, which can limit its effectiveness. To address this issue, this paper proposes an optimization approach to the construction of a sequence of benchmarks in DEA-based benchmarking, wherein two optimization criteria are employed : similarity of input-output use patterns, and proximity of input-output use levels between DMUs. To illustrate the proposed method, we applied it to the benchmarking of 23 national universities in South Korea.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2009.10a
• /
• pp.355-358
• /
• 2009

This paper proposes efficiency optimization control of IPMSM drive using multi hybrid fuzzy controller(HFC). The design of the speed controller based on fuzzy-neural network that is implemented using fuzzy control and neural network. The design of the current based on HFC using model reference and the estimation of the speed based on neural network using ANN controller. In order to maximize the efficiency in such applications, this paper proposes the optimal control method of the armature current. The controllable electrical loss which consists of the copper loss and the iron loss can be minimized by the optimal control of the armature current. The minimization of loss is possible to realize efficiency optimization control for the proposed IPMSM The optimal current can be decided according to the operating speed and the load conditions. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using multi HFC. Also, this paper proposes speed control of IPMSM using HFC1, current control of HFC2-HFC3 and estimation of speed using ANN controller. The proposed control algorithm is applied to IPMSM drive system controlled HFC, the operating characteristics controlled by efficiency optimization control are examined in detail.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.1
• /
• pp.101-107
• /
• 2008

We introduce an optimization of fuzzy set-fuzzy systems based on IG (Information Granules). The proposed fuzzy model implements system structure and parameter identification by means of IG and GAs. The concept of information granulation was coped with to enhance the abilities of structural optimization of the fuzzy model. Granulation of information realized with C-Means clustering helps determine the initial parameters of the fuzzy model such as the initial apexes of the membership functions in the premise part and the initial values of polynomial functions in the consequence part of the fuzzy rules. The initial parameters are adjusted effectively with the help of the GAs and the standard least square method. To optimally identify the structure and the parameters of the fuzzy model we exploit GAs with successive tuning method to simultaneously search the structure and the parameters within one individual. We also consider the variant generation-based evolution to adjust the rate of identification of the structure and the parameters in successive tuning method. The proposed model is evaluated with the performance of the conventional fuzzy model.

• Structural Engineering and Mechanics
• /
• v.45 no.1
• /
• pp.111-127
• /
• 2013

In this paper, a new version of gravitational search algorithm based on opposition-based learning (OBGSA) is introduced and applied for optimum design of reinforced concrete retaining walls. The new algorithm employs the opposition-based learning concept to generate initial population and updating agents' position during the optimization process. This algorithm is applied to minimize three objective functions include weight, cost and $CO_2$ emissions of retaining structure subjected to geotechnical and structural requirements. The optimization problem involves five geometric variables and three variables for reinforcement setups. The performance comparison of the new OBGSA and classical GSA algorithms on a suite of five well-known benchmark functions illustrate a faster convergence speed and better search ability of OBGSA for numerical optimization. In addition, the reliability and efficiency of the proposed algorithm for optimization of retaining structures are investigated by considering two design examples of retaining walls. The numerical experiments demonstrate that the new algorithm has high viability, accuracy and stability and significantly outperforms the original algorithm and some other methods in the literature.

• Earthquakes and Structures
• /
• v.7 no.6
• /
• pp.1119-1139
• /
• 2014

A damage-based seismic design procedure for steel frame structures is formulated as an optimization problem, in which minimization of the initial construction cost is treated as the objective of the problem. The performance constraint of the design procedure is to achieve "repairable" damage state for earthquake demands that are less severe than the design ground motions. The Park-Ang damage index is selected as the seismic damage measure for the quantification of structural damage. The charged system search (CSS) algorithm is employed as the optimization algorithm to search the optimum solutions. To improve the time efficiency of the solution algorithm, two simplifying strategies are adopted: first, SDOF idealization of multi-story building structures capable of estimating the actual seismic response in a very short time; second, fitness approximation decreasing the number of fitness function evaluations. The results from a numerical application of the proposed framework for designing a twelve-story 3D steel frame structure demonstrate its efficiency in solving the present optimization problem.