In order to solve the multi-objectiveoptimization problems of supertall buildings (such as structural design optimization, aerodynamic shape optimization, etc.) with sizable design space more effectively, it is neces...
详细信息
In order to solve the multi-objectiveoptimization problems of supertall buildings (such as structural design optimization, aerodynamic shape optimization, etc.) with sizable design space more effectively, it is necessary to develop an efficient multi-objectiveoptimization method. Therefore, generalized regression neural network optimized by genetic algorithm (GA-GRNN) based surrogate model was constructed, and a multi-objective optimization framework based on the non-dominated sorting genetic algorithm (NSGA-II) and GA-GRNN surrogate model updating was proposed. The feasibility of multi-objective optimization framework based on surrogate model updating was verified by using the experimental wind pressure data of a supertall building model, and the influencing factors of optimization efficiency were analyzed. The results show that the proposed framework has satisfactory optimization accuracy and efficiency. The optimal sample data set proportional distribution (training set: verification set: test set, i.e., T: V: T) is 7:2:1. With the increase of the total number of sample points in the design space, the optimal proportion of the initial sample points decreases significantly. A thorough consideration of the acquisition time of a single sample value and the optimal proportion of initial sample points is helpful to improve the multi-objectiveoptimization efficiency further. Therefore, for the optimization problems in engineering applications (especially supertall buildings), it is suggested that the reasonable proportion of initial sample points of the surrogate model should be determined according to the acquisition time of a single sample value and the total number of sample points in the design space. The framework is more suitable for complex problems with large total number of sample points in design space and long acquisition time of a single sample value. This study can provide a valuable reference for further research or efficient solution to multi-objectiv
Structural retrofitting is a common approach to increase the resilience of the existing buildings (e. g., office buildings) in the industrial (e.g., refinery) sites against earthquakes. In this study, a typical RC str...
详细信息
Structural retrofitting is a common approach to increase the resilience of the existing buildings (e. g., office buildings) in the industrial (e.g., refinery) sites against earthquakes. In this study, a typical RC structure that used as operational office building is considered, for which a multiobjectiveframework is proposed to select the retrofit patterns that are optimized for seismic resilience index and cost of retrofit of these buildings. For this purpose, three different jacketing materials (i.e., Steel, CFRP and GFRP) with four various thicknesses for each one (1.2, 2.4, 3.6 and 4.8 mm for Steel, and 1 to 4 plies for CFRP and GFRP) are chosen to retrofit these buildings. In addition, six different plans are considered for the retrofit designs. Besides, three seismic intensity levels from low to severe seismic intensities with different distances ranging from near-to far-field are taken into account to determine the sensitivity of responses. For each scenario, the fragility values for calculating the seismic resilience index, and the cost of retrofit are obtained, and then the optimal set of solutions is calculated by applying the well-established non-dominated sorting genetic algorithm II. The results show that the structural retrofitting not only reduces the sensitivity of the structural response to different seismic inputs in a limited range, but also improves the performance of the structure in terms of resilience index especially at higher intensities. The proposed framework provides a method for decision makers to choose optimal retrofit strategies that minimize the corresponding costs, while achieving a predesigned resilience's level for an infrastructure system.
Each of the total Life-Cycle Cost (LCC) and resilience index are valuable indicators of infrastructure management against hazard events during its service lifetime. In this study, the proposed multi-objective framewor...
详细信息
Each of the total Life-Cycle Cost (LCC) and resilience index are valuable indicators of infrastructure management against hazard events during its service lifetime. In this study, the proposed multi-objectiveframework provides a systematic methodology for decision-makers to select the optimal retrofit strategies that minimize the LCC while satisfying a given level of resilience, for which various retrofit strategies are chosen. For each case, the fragility curves are established through IDA for calculating the resilience and LCC, which incorporates the effects of complete or incomplete repair actions of damage conditions induced by multiple occurrences of previous hazard events. This study employs a well-known 'NSGA II' to identify the optimal set of solutions. The various aspects of the optimal retrofit strategies are thoroughly investigated and discussed for an actual structure in the refinery sites as a case study infrastructure.
Silicone material extrusion(MEX)is widely used for processing liquids and *** to the uneven linewidth and elastic extrusion deformation caused by material accumulation,products may exhibit geometric errors and perform...
详细信息
Silicone material extrusion(MEX)is widely used for processing liquids and *** to the uneven linewidth and elastic extrusion deformation caused by material accumulation,products may exhibit geometric errors and performance defects,leading to a decline in product quality and affecting its service *** study proposes a process parameter optimization method that considers the mechanical properties of printed specimens and production *** improve the quality of silicone printing samples and reduce production costs,three machine learning models,kernel extreme learning machine(KELM),support vector regression(SVR),and random forest(RF),were developed to predict these three *** data were obtained through a complete factorial experiment.A new dataset is obtained using the Euclidean distance method,which assigns the elimination *** is trained with Bayesian optimization algorithms for parameter optimization,the new dataset is input into the improved double Gaussian extreme learning machine,and finally obtains the improved KELM *** results showed improved prediction accuracy over SVR and ***,a multi-objective optimization framework was proposed by combining genetic algorithm technology with the improved KELM *** effectiveness and reasonableness of the model algorithm were verified by comparing the optimized results with the experimental results.
The integration of renewable energy and electric vehicles in smart grids aims to improve the grid network and reduce carbon emissions. In this regard, this study presents a new Energy Management Scheme (EMS) for the o...
详细信息
ISBN:
(纸本)9781665403450
The integration of renewable energy and electric vehicles in smart grids aims to improve the grid network and reduce carbon emissions. In this regard, this study presents a new Energy Management Scheme (EMS) for the optimal charging and discharging of electric vehicles in a photovoltaic-present distribution network based on the availability of solar energy and power from the grid. For effective scheduling, the model splits a distribution network into residential and commercial areas, which are handled separately by two Electric Vehicle (EV) aggregators. A newly developed hybrid algorithm, named Chaotic Whale optimization Algorithm and Gravitational Search Algorithm (CWOAGSA), is integrated into a multiobjectiveframework to simultaneously minimize power loss, improve voltage stability, and reduce carbon emissions. Simulation results show that the proposed model can inject real power at a 60% EV penetration level without destabilizing the distribution network. The comparison of the CWOAGSA to the WOA, PSO, and GA shows a better minimization of real power loss. The CWOAGSA minimizes the total real power network losses with a 55% margin from the increased power loss due to the uncoordinated scheduling, and a 7% margin to the WOA.
暂无评论