• Geomechanics and Engineering
• /
• v.28 no.4
• /
• pp.385-396
• /
• 2022

The accurate determination of the subgrade reaction modulus (K_s) of soil is an important factor for geotechnical engineers. This study estimated the K_s of soft soil improved with floating deep cement mixing (DCM) columns. A novel prediction model was developed that emphasizes the accuracy of identifying the most significant parameters of K_s. Several multi-layer perceptron (MLP) models that were trained using the Levenberg Marquardt (LM) backpropagation method were developed to estimate K_s. The models were trained using a reliable database containing the results of 36 physical modelling tests. The input parameters were the undrained shear strength of the DCM columns, undrained shear strength of soft soil, area improvement ratio and length-to-diameter ratio of the DCM columns. Grey wolf optimization (GWO) was coupled with the MLPs to improve the performance indices of the MLPs. Sensitivity tests were carried out to determine the importance of the input parameters for prediction of K_s. The results showed that both the MLP-LM and MLP-GWO methods showed high ability to predict K_s. However, it was shown that MLP-GWO (R = 0.9917, MSE = 0.28 (MN/m²/m)) performed better than MLP-LM (R =0.9126, MSE =6.1916 (MN/m²/m)). This proves the greater reliability of the proposed hybrid model of MLP-GWO in approximating the subgrade reaction modulus of soft soil improved with floating DCM columns. The results revealed that the undrained shear strength of the soil was the most effective factor for estimation of K_s.

• Nuclear Engineering and Technology
• /
• v.53 no.1
• /
• pp.148-163
• /
• 2021

Timely fault identification is important for safe and reliable operation of the electric valve system. Many research works have utilized different data-driven approach for fault diagnosis in complex systems. However, they do not consider specific characteristics of critical control components such as electric valves. This work presents an integrated shallow-deep fault diagnostic model, developed based on signals extracted from DN50 electric valve. First, the local optimal issue of particle swarm optimization algorithm is solved by optimizing the weight search capability, the particle speed, and position update strategy. Then, to develop a shallow diagnostic model, the modified particle swarm algorithm is combined with support vector machine to form a hybrid improved particle swarm-support vector machine (IPs-SVM). To decouple the influence of the background noise, the wavelet packet transform method is used to reconstruct the vibration signal. Thereafter, the IPs-SVM is used to classify phase imbalance and damaged valve faults, and the performance was evaluated against other models developed using the conventional SVM and particle swarm optimized SVM. Secondly, three different deep belief network (DBN) models are developed, using different acoustic signal structures: raw signal, wavelet transformed signal and time-series (sequential) signal. The models are developed to estimate internal leakage sizes in the electric valve. The predictive performance of the DBN and the evaluation results of the proposed IPs-SVM are also presented in this paper.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.95-100
• /
• 2023

Due to Traffic accidents people faces health and economical casualties around the world. As the population increases vehicles on road increase which leads to congestion in cities. Congestion can lead to increasing accident risks due to the expansion in transportation systems. Modern cities are adopting various technologies to minimize traffic accidents by predicting mathematically. Traffic accidents cause economical casualties and potential death. Therefore, to ensure people's safety, the concept of the smart city makes sense. In a smart city, traffic accident factors like road condition, light condition, weather condition etcetera are important to consider to predict traffic accident severity. Several machine learning models can significantly be employed to determine and predict traffic accident severity. This research paper illustrated the performance of a hybridized neural network and compared it with other machine learning models in order to measure the accuracy of predicting traffic accident severity. Dataset of city Leeds, UK is being used to train and test the model. Then the results are being compared with each other. Particle Swarm optimization with artificial neural network (PSO-ANN) gave promising results compared to other machine learning models like Random Forest, Naïve Bayes, Nearest Centroid, K Nearest Neighbor Classification. PSO- ANN model can be adopted in the transportation system to counter traffic accident issues. The nearest centroid model gave the lowest accuracy score whereas PSO-ANN gave the highest accuracy score. All the test results and findings obtained in our study can provide valuable information on reducing traffic accidents.

• Journal of Hydrogen and New Energy
• /
• v.34 no.4
• /
• pp.358-368
• /
• 2023

The fuel cell market is expected to grow rapidly. Therefore, it is necessary to scale up fuel cells for buildings, power generation, and ships. A multi-stack system can be an effective way to expand the capacity of a fuel cell. Multi-stack fuel cell systems are better than single-stack systems in terms of efficiency, reliability, durability and maintenance. In this research, we developed a residential fuel cell stack and system model that generates electricity using the fuel cell-photovoltaic hybrid system. The efficiency and hydrogen consumption of the fuel cell system were calculated according to the three proposed power distribution methods (equivalent, Daisy-chain, and optimal method). As a result, the optimal power distribution method increases the efficiency of the fuel cell system and reduces hydrogen consumption. The more frequently the multi-stack fuel cell system is exposed to lower power levels, the greater the effectiveness of the optimal power distribution method.

• Geomechanics and Engineering
• /
• v.31 no.2
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.35 no.3
• /
• pp.229-235
• /
• 2011

This research aims todevelopa compression/absorption hybrid heat pump system using an $NH_3/H_2O$ as working fluid.The heatpump cycle is based on a combination of compression and absorption cycles. The cycle consists of two-stage compressors, absorbers, a desorber, a desuperheater, solution heat exchangers, a solution pump, a rectifier, and a liquid/vapor separator. The compression/absorption hybrid heat pump was designed to produce hot water above $90^{\circ}C$ using high-temperature glide during a two-phase heat transfer. Distinct characteristics of the nonlinear temperature profile should be considered to maximize the performance of the absorber. In this study, the performance of the absorber was investigated depending on the capacity, shape, and arrangementof the plate heat exchangers with regard tothe concentration and distribution at the inlet of the absorber.

• Korean Chemical Engineering Research
• /
• v.58 no.3
• /
• pp.381-389
• /
• 2020

This study analyzed the optimal electricity cost of a 100% renewable energy source (RES) based system. Especially energy storage system (EES) and supplementary biopower system as well as photovoltaic (PV) and wind power component were included in the proposed RES-based system to overcome the intermittence of RESs and to efficiently balance energy supply and demand. To comparatively analyze the levelized cost of electricity (LCOE) of different RES-based systems, six scenarios were developed according to the involved RESs: PV, wind, PV/wind, PV/biopower, wind/biopower, and PV/wind/biopower systems. We then applied the proposed systems to build a 100% RES-based system in Jeju Island, Korea. As a result, the single component based system, PV and wind power system of 0.18 and 0.28 $/kWh, respectively, cannot compete with the economics of existing electricity grid. However, the optimal LCOE of the hybrid system where PV and wind power are used as main supply options and biopower as supplementary option was identified to be 0.08 $/kWh, which can compete with the economics of an existing electricity grid.

• Journal of Wetlands Research
• /
• v.19 no.3
• /
• pp.271-278
• /
• 2017

Low impact development (LID) technology has been recently applied for the treatment of nonpoint source pollutants. Rain garden is one of the widely used LIDs since it utilizes various mechanisms such as biological and physico-chemical treatment to reduce pollutants. However, problem such as clogging has been one of the issues encountered by the rain garden that do not undergo constant maintenance. Therefore, this research was conducted to develop and determine the component arrangement of a rain garden system for a more efficient volume and pollutant reduction. Two hybrid rain garden systems having different characteristics were developed and evaluated to determine the optimum design and arrangement of the system. The results showed that the components arranged in a series manner showed a volume reduction of 93% and a pollutant reduction efficiency of approximately 99%, 93% and 95% was observed for particulates, nutrients and heavy metals, respectively. While when the system is connected in a combined series-parallel, the volume and average pollutant reduction efficiency for the TSS, nutrients and heavy metals are 65%, 94%, 80% and 85%, respectively. Moreover, the component arrangement in the order of sedimentation tank, infiltration tank and plant bed exhibited a high pollutant reduction efficiency compared when the infiltration tank and plant bed were interchanged. The findings of this research will help in the further development and optimization of rain garden systems.

• Plant Journal
• /
• v.9 no.3
• /
• pp.38-42
• /
• 2013

Submarine gas fields have focused because of the increasing fuel cost, the environmental regulations, and the safety & NIMBY problems. LNG-FPSO which is available for acid gas removal, recovery of the condensate & LPG and Liquefaction in topside process is one of high technology offshore structures. On the other hands, it is necessary to verify the pre-treatment efficiency by the ship motion and to apply to the design for LNG-FPSO. This study is to develop the pre-treatment technology for LNG-FPSO as taking account to the process efficiency by ship motion effects and the area optimization. Based on the simulation results, it founds that hybrid process shows the low circulate rate, the low heat duty and the small size of column dimensions compared to typical amine process. It will be verified the process efficiency in the various conditions by sea states as performing the 6-DOF motion test and CFD simulation.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.6
• /
• pp.596-600
• /
• 2013

We report here on the processing and manufacturing of thin film for printed electronics by micro-gravure coating system. The micro-gravure coating systems are consisted of various modules such as web and system tension controller, micro-gravure coating units, dispenser and hybrid dry units (UV, NIR, Hot air). Especially, for the optimization of system, the number of idle roller was minimized and tension isolating infeeder was included. Also, we applied four patterns circle, 45 degree, square and 35 degree for the optimizing coating thickness. The micro-gravure coating system which applied various patterns to enable continuous coating process and fast coating time compare with conventional batch coating system. In this paper, introduce of micro-gravure coating system and testing results of coating thickness (20~700nm), coating time (1~2sec) and surface roughness (3~12nm) by using micro-gravure coating system.