|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine显示文摘Plastic concrete is an engineering material,which is commonly used for construction of cut-offwalls to prevent water seepage under the dam.This paper aims to explore two machine learning algorithms including artificial neural network (ANN)and support vector machine (SVM)to predict the compressive strength of bentonite/sepiolite plastic concretes.For this purpose,two unique sets of 72 data for compressive strength of bentonite and sepiolite plastic concrete samples (totally 144 data)were prepared by conducting an experimental study.The results confirm the ability of ANN and SVM models in prediction processes.Also,Sensitivity analysis of the best obtained model indicated that cement and silty clay have the maximum and minimum influences on the compressive strength,respectively.In addition, investigation of the effect of measurement error of input variables showed that change in the sand content (amount)and curing time will have the maximum and minimum effects on the output mean absolute percent error (MAPE)of model, respectively.Finally,the influence of different variables on the plastic concrete compressive strength values was evaluated by conducting parametric studies. | Ali Reza GHANIZADEH Hakime ABBASLOU Amir Tavana AMLASHI Pourya ALIDOUST | 2019 | Frontiers of Structural and Civil Engineering2019，13，1： | 3 |
| 2 | Combining artificial neural network and multi-objective optimization to reduce a heavy-duty diesel engine emissions and fuel consumption显示文摘Nondominated sorting genetic algorithm Ⅱ(NSGA-Ⅱ) is well known for engine optimization problem. Artificial neural networks(ANNs) followed by multi-objective optimization including a NSGA-Ⅱ and strength pareto evolutionary algorithm(SPEA2) were used to optimize the operating parameters of a compression ignition(CI) heavy-duty diesel engine. First, a multi-layer perception(MLP) network was used for the ANN modeling and the back propagation algorithm was utilized as training algorithm. Then, two different multi-objective evolutionary algorithms were implemented to determine the optimal engine parameters. The objective of the present study is to decide which algorithm is preferable in terms of performance in engine emission and fuel consumption optimization problem. | Amir-Hasan Kakaee Pourya Rahnama Amin Paykani Behrooz Mashadi | 2015 | Journal of Central South University2015，22，11： | 3 |
| 3 | Influence of random heterogeneity of shear wave velocity on sliding mass response and seismic deformations of earth slopes显示文摘Soil shear wave velocity has been recognized as a governing parameter in the assessment of the seismic response of slopes.The spatial variability of soil shear wave velocity can influence the seismic response of sliding mass and seismic displacements.However,most analyses of sliding mass response have been carried out by deterministic models.This paper stochastically investigates the effect of random heterogeneity of shear wave velocity of soil on the dynamic response of sliding mass using the correlation matrix decomposition method and Monte Carlo simulation(MCS).The software FLAC 7.0 along with a Matlab code has been utilized for this purpose.The influence of statistical parameters on the seismic response of sliding mass and seismic displacements in earth slopes with different inclinations and stiffnesses subject to various earthquake shakings was investigated.The results indicated that,in general,the random heterogeneity of soil shear modulus can have a notable impact on the sliding mass response and that neglecting this phenomenon could lead to underestimation of sliding deformations. | Pourya Kazemi Esfeh Bahram Nadi Nicholas Fantuzzi | 2020 | Earthquake Engineering and Engineering Vibration2020，19，2： | 2 |
| 4 | Electrocatalytic determination of sulfite using a modified carbon nanotubes paste electrode: application for determination of sulfite in real samples显示文摘 | Hassan Karimi-Maleh Ali Ensafi Hadi Beitollahi Vahid Nasiri Mohammad Khalilzadeh Pourya Biparva | 2012 | Ionics2012，，7： | 1 |
| 5 | Secondary flows in statistically unstable turbulent boundary layers with spanwise heterogeneous roughness显示文摘Large-scale secondary motions are known to occur in turbulent flows over surfaces with spanwise roughness heterogeneity.Numerical studies often use adjacent high-and low-roughness longitudinal strips to investigate these secondary rolls in boundary layers without any thermal stratification.In the present study,the effect of unstable thermal stratification on secondary rolls in a very high-Reynolds-number turbulent flow with spanwise-heterogeneous roughness is investigated by means of large-eddy simulation.The strength of the unstable stratification is systematically changed from L/h=−20 to L/h=−1,where L and h are Monin-Obukhov length and boundary-layer height,respectively.This range covers the transition from neutral stratification to unstable stratification.The results show that the positive buoyancy associated with the unstable thermal stratification acts against the roughness-induced secondary rolls.In the case of unstable stratification,secondary rolls are completely canceled out by buoyancy and replaced by new stronger convection-induced rolls rotating in opposite directions. | Ali Amarloo Pourya Forooghi Mahdi Abkar | 2022 | Theoretical & Applied Mechanics Letters2022，12，2： | 1 |
| 6 | Stability Assessment of a DC Distribution Network in a Hybrid Micro-grid Application 显示文摘 | SHAMSI Pourya FAHIMI Babak | 2014 | IEEE Transactions on Smart Grid2014，5，5： | 1 |
| 7 | Fuzzy Logic-based Load-frequency Control Concerning High Penetration of Wind Turbines显示文摘 | BEVRANI Hassan DANRDHMAND Pourya Ranjbar | 2012 | IEEE Systems Journal2012，06，1： | 1 |
| 8 | EMC Improvement for High Voltage Pulse Transformers by Pareto-optimal Design of a Geometry Structure Based on Parasitic Analysis and EMI Propagation显示文摘High voltage pulse transformers have an essential role in pulsed power systems and power conversion applications.Improving the electromagnetic behavior of such devices leads to better efficiency and low-level electromagnetic interference(EMI)noise propagation in systems.In this paper,a high voltage pulsed power system is considered and analyzed to improve their electromagnetic compatibility(EMC).The new generation of pulsed power systems that use SiC and GaN fast switches in capacitor charger power electronic circuits,face far more EMI challenges.Moreover,in this paper,the EMI propagation paths in the pulsed power system are realized and analyzed.The EMI noise level of the system is obtained and compared to the IEC61800-3 standard.To improve the EMC,the parasitic parameters of the transformer,as the main path of EMI circulation,are optimized to block the EMI propagation in the pulsed power system.To achieve this result,the parasitics are modeled and calculated with a novel and accurate energy distribution model.Then,by defining a cost function,the geometry structure of the transformer is optimized to lower the parasitics in the system.Three pareto-optimal techniques are investigated for the cost function optimization.The models and results are verified by the 3D-finite element method(FEM)and experimental results for several given scenarios.FEM and experimental verifications of this model,make the model suitable for any desirable design in any pulsed power system.Finally,the EMI noise level of the system after optimization is shown and compared to the IEC61800-3 standard. | Mohamad Saleh Sanjari Nia Pourya Shamsi Mehdi Ferdowsi | 2021 | CSEE Journal of Power and Energy Systems2021，7，5： | 1 |
| 9 | Combining flamelet-generated manifold and machine learning models in simulation of a non-premixed diffusion flame显示文摘Flamelet Generated Manifold(FGM)is an example of a chemistry tabulation or a flamelet method that is under attention because of its accuracy and speed in predicting combustion characteristics.However,the main problem in applying the model is a large amount of memory required.One way to solve this problem is to apply machine learning(ML)to replace the stored tabulated data.Four different machine learning methods,including two Artificial Neural Networks(ANNs),a Random Forest(RF),and a Gradient Boosted Trees(GBT),are trained,validated,and compared in terms of various performance measures.The progress variable source term and transport properties are replaced with the ML models.Particular attention was paid to the progress variable source term due to its high gradient and wide range of its value in the control variables space.Data preprocessing is shown to play an essential role in improving the performance of the models.Two ensemble models,namely RF and GBT,exhibit high training efficiency and acceptable accuracy.On the other hand,the ANN models have lower training errors and take longer to train.The four models are then combined with a one-dimensional combustion code to simulate a counterflow non-premixed diffusion flame in engine-relevant conditions.The predictions of the ML-FGM models are compared with detailed chemical simulations and the original FGM model for key combustion properties and representative species profiles. | Kaimeng Li Pourya Rahnama Ricardo Novella Bart Somers | 2023 | Energy and AI2023，14，4： | 0 |
| 10 | Preparation of Antibacterial Cotton Wound Dressing By Green Synthesis Silver Nanoparticles Using Mullein Leaves Extract显示文摘Silver nanoparticles(AgNPs)were synthesized by a bio-reduction method using an aqueous extract of mullein leaves(Verbascum thapsus L.)functioning as reducing as well as a stabilizing agent.Various synthesis parameters such as reaction time,temperature and concentration of the extract were also studied for the synthesis of AgNPs.The so prepared AgNPs were characterized by various techniques including UV-Vis spectroscopy,X-ray diffraction,scanning electron microscopy(equipped with energy dispersive analysis of X-rays),and transmission electron microscopy.The electron microscopy images suggest the formation of polydispersed spherical AgNPs with average particle size of about 20 nm.The kinetic analysis revealed that the rate of bio-reduction of silver ions was very slow for initial 1h;however,later the reduction was fast as the development of characteristic color of AgNPs was completed within 5 hrs.This observation was concomitant with the appearance of the surface plasmon absorbance peak at~430 nm.Further,these nanoparticles were used for the treatment of wound dressings by the exhaustion method.The so developed wound dressings showed good antibacterial activity against a gram positive bacterial strain Staphylococcus aureus. | S.Najmeh Aboutorabi Majid Nasiriboroumand Pourya Mohammadi Hassan Sheibani Hossein Barani | 2019 | Journal of Renewable Materials2019，7，8： | 0 |
| 11 | 室温下Cu掺杂的ZnO纳米粉末催化多组分一锅法合成完全取代的茚并[1,2-b]吡啶(英文)显示文摘Cu doped ZnO nanocrystalline powder(10 mol%) has been found to be an efficient catalyst for the one‐pot multi‐component synthesis of fully substituted new indeno[1,2‐b]pyridines through a com-bination of 1,3‐indandione, propiophenone or acetophenone derivatives, aromatic aldehydes, and ammonium acetate in ethanol/H2 O at room temperature. The methodology is mild, efficient and high to excellent yielding. | Heshmatollah Alinezhad Sahar Mohseni Tavakkoli Pourya Biparva 鄢洪德 | 2014 | 催化学报2014，35，4： | 0 |
| 12 | Antibacterial,antioxidative and sensory properties of Ziziphora clinopodioides–Rosmarinus officinalis essential oil nanoencapsulated using sodium alginate in raw lamb burger patties显示文摘This study was aimed to encapsulate Ziziphora clinopodioides –Rosmarinus officinalis essential oil (Z-REO) using sodium alginate (NaAlg) and to evaluate its performance on antimicrobial and antioxidative activities and sensory attributes in lamb burger patties during cold storage for 12 days.GC-MS analysis of Z-REO indicated carvacrol (21.5%) and thymol (16.9%) were the major components.SEM images showed the formation of encapsulated particles.The presence of encapsulated Z-REO in NaAlg was proved based on the increase in band intensity of FTIR spectra.By increasing mass ratios of NaAlg:Z-REO from 1:1 to 2:1,and 4:1,encapsulation efficiency was increased.Average zeta-potential values (mV) of the mass ratios 4:1 and 2:1 were −48.67 and −44.83,indicating the stability of encapsulated particles.The average size of particles ranged from 159.14 nm to 256.14 nm.The results showed that the encapsulated nanoparticles could markedly decrease the growth of inoculated Escherichia coli O157:H7 and Staphylococcus aureus and delay the lipid oxidation of lamb patties compared to the control samples and in samples with free Z-REO.Furthermore,nanoparticles efficiently decreased discoloration and off-odor development in the patties.Therefore,NaAlg-Z-REO nanoparticles could efficiently reduce bacterial growth and oxidative or sensory deterioration of lamb patties during storage. | Pourya Karimifar S.Siavash Saei-Dehkordi Zahra Izadi | 2022 | Food Bioscience2022，47，3： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员