Shear connectors play a prominent role in the design of steel-concrete composite systems. The behavior of shear connectors is generally determined through conducting push-out tests. However, these tests are costly and require plenty of time. As an alternative approach, soft computing (SC) can be used to eliminate the need for conducting push-out tests. This study aims to investigate the application of artificial intelligence (AI) techniques, as sub-branches of SC methods, in the behavior prediction of an innovative type of C-shaped shear connectors, called Tilted Angle Connectors. For this purpose, several push-out tests are conducted on these connectors and the required data for the AI models are collected. Then, an adaptive neuro-fuzzy inference system (ANFIS) is developed to identify the most influencing parameters on the shear strength of the tilted angle connectors. Totally, six different models are created based on the ANFIS results. Finally, AI techniques such as an artificial neural network (ANN), an extreme learning machine (ELM), and another ANFIS are employed to predict the shear strength of the connectors in each of the six models. The results of the paper show that slip is the most influential factor in the shear strength of tilted connectors and after that, the inclination angle is the most effective one. Moreover, it is deducted that considering only four parameters in the predictive models is enough to have a very accurate prediction. It is also demonstrated that ELM needs less time and it can reach slightly better performance indices than those of ANN and ANFIS.
With growing use of roadheaders in the world and its significant role in the successful accomplishment of a tunneling project, it is a necessity to accurately predict performance of this machine in different ground conditions. On the other hand, the existence of some shortcomings in the prediction models has made it necessary to perform more research on the development of the new models. This paper makes an attempt to model the rate of roadheader performance based on the geotechnical and geological site conditions. For achieving the aim, an artificial neural network (ANN), a powerful tool for modeling and recognizing the sophisticated structures involved in data, is employed to model the relationship between the roadheader performance and the parameters influencing the tunneling operations with a high correlation. The database used in modeling is compiled from laboratory studies conducted at Azad University at Science and Research Branch, Tehran, Iran. A model with architecture 4-10-1 trained by back-propagation algorithm is found to be optimum. A multiple variable regression (MVR) analysis is also applied to compare performance of the neural network. The results demonstrate that predictive capability of the ANN model is better than that of the MVR model. It is concluded that roadheader performance could be accurately predicted as a function of unconfined compressive strength, Brazilian tensile strength, rock quality designation, and alpha angle R2 = 0.987. Sensitivity analysis reveals that the most effective parameter on roadheader performance is the unconfined compressive strength. 相似文献
Silicon - SiO2 nano-particles are applied in different industries such as ceramic producing, glass making, cosmetic products, medicines, magnetic mixtures, heat and electric insulators and glazing... 相似文献
The adsorption and desorption behavior of a planar microfabricated preconcentrator (PC) has been modeled and simulated using the computational fluid dynamics (CFD) package CFDRC-ACE+trade. By comparison with the results of a designed experiment, model parameters were determined. Assuming a first-order reaction for the adsorption of a light hydrocarbon chemical analyte onto the PC adsorbent and a unity-value sticking coefficient, a rate constant of 36 500 s-1 was obtained. This compares favorably with the value of 25 300 s-1 obtained by application of the Modified-Wheeler equation. The modeled rate constant depends on the concentration of adsorbent sites, estimated to be 6.94 ldr 10-8 kmol/m2 for the Carboxen 1000 adsorbent used. Using the integral method, desorption was found to be first order with an Arrhenius temperature dependence and an activation energy of 30.1 kj/mol. Validation of this model is reported herein, including the use of Aris-Taylor dispersion to predict the influence of fluidics surrounding the PC. A maximum in desorption peak area with flow rate, predicted from a quadratic fit to the results of the designed experiment, was not observed in the 2-D simulation. Either approximations in the simulated model or the nonphysical nature of the quadratic fit are responsible. Despite the apparent simplicity of the model, the simulation is internally self consistent and capable of predicting performance of new device designs. To apply the method to other analytes and other adsorbent materials, only a limited number of comparisons to experiment are required to obtain the necessary rate constants. 相似文献
In this work, a comparison of co-current and counter-current modes of operation for a novel hydrogen-permselective membrane reactor for Fischer-Tropsch Synthesis (FTS) has been carried out. In both modes of operations, a system with two-catalyst bed instead of one single catalyst bed is developed for FTS reactions. In the first catalytic reactor, the synthesis gas is partly converted to products in a conventional water-cooled fixed-bed reactor, while in the second reactor which is a membrane fixed-bed reactor, the FTS reactions are completed and heat of reaction is used to preheat the feed synthesis gas to the first reactor. In the co-current mode, feed gas is entered into the tubes of the second reactor in the same direction with the reacting gas stream in shell side while in the counter-current mode the gas streams are in the opposite direction. Simulation results for both co-current and counter-current modes have been compared in terms of temperature, gasoline and CO2 yields, H2 and CO conversion, selectivity of components as well as permeation rate of hydrogen through the membrane. The results showed that the reactor in the co-current configuration operates with lower conversion and lower permeation rate of hydrogen, but it has more favorable profile of temperature. The counter-current mode of operation decreases undesired products such as CO2 and CH4 and also produces more gasoline. 相似文献
Pure hydrogen was produced by means of chemical looping steam methane reforming with novel oxygen carriers. Ni-ferrite, Ni-ferrite-ZrO2, and Ni-ferrite-CeO2 were synthesized as oxygen carriers and characterized by X-ray diffraction (XRD), Brunauer-Emmett-Teller (BET) method, scanning electron microscopy (SEM), dynamic light scattering (DLS), and hydrogen temperature-programmed reduction (H2-TPR). The performances of the as-synthesized oxygen carriers in the cyclic oxidation-reduction were investigated in the packed-bed microreactor at a defined temperature range and under atmospheric pressure. Ni0.39Fe2.61O4-ZrO2 exhibited the best performance and maximum methane conversion among the other oxygen carriers. In addition, high selectivities for H2 and CO were reached. 相似文献
Evaluation of the parameters affecting the shear strength and ductility of steel–concrete composite beam is the goal of this study. This study focuses on predicting the future output of beam’s strength and ductility based on relative inputs using a soft computing scheme, extreme learning machine (ELM). Estimation and prediction results of the ELM models were compared with genetic programming (GP) and artificial neural networks (ANNs) models. Referring to the experimental results, as opposed to the GP and ANN methods, the ELM approach enhanced generalization ability and predictive accuracy. Moreover, achieved results indicated that the developed ELM models can be used with confidence for further work on formulating novel model predictive strategy in shear strength and ductility of steel concrete composite. Furthermore, the experimental results indicate that on the whole, the newflanged algorithm creates good generalization presentation. In comparison to the other widely used conventional learning algorithms, the ELM has a much faster learning ability. 相似文献
Improving the octane number of the aromatics’ compounds has always been an important matter in refineries and lots of investigations have been made concerning this issue. In this study, an axial-flow spherical packed-bed reactor (AF-SPBR) is considered for naphtha reforming process in the presence of catalyst deactivation. Model equations are solved by the orthogonal collocation method. The AF-SPBR results are compared with the plant data of a conventional tubular packed-bed reactor (TR). The effects of some important parameters such as pressure and temperature on aromatic and hydrogen production rates and catalyst activity have been investigated. Higher production rates of aromatics can successfully be achieved in this novel reactor. Moreover, results show the capability of flow augmentation in the proposed configuration in comparison with the TR. This study shows the superiority of AF-SPBR configuration to the conventional types. 相似文献