A novel approach to predict shear strength of tilted angle connectors using artificial intelligence techniques

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.

     

Predicting roadheader performance by using artificial neural network

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 R ² = 0.987. Sensitivity analysis reveals that the most effective parameter on roadheader performance is the unconfined compressive strength.     

Developing an Interactive Spatial Multi-Attribute Decision Support System for Assessing Water Resources Allocation Scenarios

Water Resources Management - In water resource management, assessing water resource allocation scenarios (WRASs) is an important multi-attribute decision making (MADM) problem. It involves...     

Effects of stray magnetic forces on position error signals during a long seeking-and-settling process

This paper is to study how stray magnetic forces encountered in a long seeking process affect position errors of a hard disk drive after it finishes the seek and settles. The study consists of three parts: analysis of stray magnetic forces, numerical modeling, and analysis of numerical results. In the analysis of stray magnetic forces, we lump the stray magnetic forces into three components D1, D2 and D4. Specifically, D1 is a pair of stray magnetic forces in the plane of the voice coil. The two forces act on the two equal legs of the voice coil. In addition, the two forces point to and away from the pivot center, respectively. D2 is a pair of stray magnetic forces out of the plane of the voice coil. The two forces are equal in magnitudes but opposite in directions. The two force components also act on the two equal legs of the voice coil. D4 is identical to D2, except that the two force components in D4 act in the same direction. In the numerical study, we adopt a numerical model that includes a spinning spindle motor, a spinning disk pack with multiple disks, a stationary base plate with a top cover, and a slewing head-stack assembly. Moreover, multiple bearings are present in the model to connect the multiple components. In particular, fluid-dynamic bearings connect the rotating spindle and disk pack with the base plate, pivot bearings connect the base plate with the head-stack assembly, and air bearings connect the spinning disk pack with head sliders located at the tip of the slewing head-stack assembly. Also, the numerical model assumes that the head-stack assembly seeks according to a user-specified seeking profile. Numerical simulations show two major conclusions. First, stray magnetic force component D1 does not lead to significant position errors when the head-stack assembly settles. Stray magnetic force components D2 and D4, however, can affect the position errors by significantly exciting torsion and bending modes of the head-stack assembly. Second, a flex cable can significantly increase position errors below 1 kHz during settling.     

A Case Study on Optimization of Biomass Flow During Single-Screw Extrusion Cooking Using Genetic Algorithm (GA) and Response Surface Method (RSM)

In the present study, response surface method (RSM) and genetic algorithm (GA) were used to study the effects of process variables like screw speed, rpm (x ₁), L/D ratio (x ₂), barrel temperature (°C; x ₃), and feed mix moisture content (%; x ₄), on flow rate of biomass during single-screw extrusion cooking. A second-order regression equation was developed for flow rate in terms of the process variables. The significance of the process variables based on Pareto chart indicated that screw speed and feed mix moisture content had the most influence followed by L/D ratio and barrel temperature on the flow rate. RSM analysis indicated that a screw speed?>?80 rpm, L/D ratio?>?12, barrel temperature?>?80 °C, and feed mix moisture content?>?20% resulted in maximum flow rate. Increase in screw speed and L/D ratio increased the drag flow and also the path of traverse of the feed mix inside the extruder resulting in more shear. The presence of lipids of about 35% in the biomass feed mix might have induced a lubrication effect and has significantly influenced the flow rate. The second-order regression equations were further used as the objective function for optimization using genetic algorithm. A population of 100 and iterations of 100 have successfully led to convergence the optimum. The maximum and minimum flow rates obtained using GA were 13.19?×?10^?7 m³/s (x ₁?=?139.08 rpm, x ₂?=?15.90, x ₃?=?99.56 °C, and x ₄?=?59.72%) and 0.53?×?10^?7 m³/s (x ₁?=?59.65 rpm, x ₂?=?11.93, x ₃?=?68.98 °C, and x ₄?=?20.04%).     

Sensory and Physicochemical Studies of Thermally Micronized Chickpea (Cicer arietinum) and Green Lentil (Lens culinaris) Flours as Binders in Low‐Fat Beef Burgers

Pulses are known to be nutritious foods but are susceptible to oxidation due to the reaction of lipoxygenase (LOX) with linolenic and linoleic acids which can lead to off flavors caused by the formation of volatile organic compounds (VOCs). Infrared micronization at 130 and 150 °C was investigated as a heat treatment to determine its effect on LOX activity and VOCs of chickpea and green lentil flour. The pulse flours were added to low‐fat beef burgers at 6% and measured for consumer acceptability and physicochemical properties. Micronization at 130 °C significantly decreased LOX activity for both flours. The lentil flour micronized at 150 °C showed a further significant decrease in LOX activity similar to that of the chickpea flour at 150 °C. The lowering of VOCs was accomplished more successfully with micronization at 130 °C for chickpea flour while micronization at 150 °C for the green lentil flour was more effective. Micronization minimally affected the characteristic fatty acid content in each flour but significantly increased omega‐3 and n‐6 fatty acids at 150 °C in burgers with lentil and chickpea flours, respectively. Burgers with green lentil flour micronized at 130 and 150 °C, and chickpea flour micronized at 150 °C were positively associated with acceptability. Micronization did not affect the shear force and cooking losses of the burgers made with both flours. Formulation of low‐fat beef burgers containing 6% micronized gluten‐free binder made from lentil and chickpea flour is possible based on favorable results for physicochemical properties and consumer acceptability.     

Potential of soft computing approach for evaluating the factors affecting the capacity of steel–concrete composite beam

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.     

Enhancing liquid micromixing using low‐frequency rotating nanoparticles

Magnetic nanofluid actuation by rotating magnetic fields was proposed as a high‐performance tool for liquid mixing with enhanced micromixing features. A comparative study was conducted to evaluate the mixing index in T‐type mixers of magnetic and nonmagnetic fluids subject to static (SMF), oscillating (OMF), and rotating (RMF) magnetic fields. RMF excitation unveiled superior mixing indices with strong dependences to magnetic field frequency and content of magnetic nanoparticles. The impact of magnetic field types on micromixing was further examined at low and moderate Re numbers using the Villermaux–Dushman reaction and IEM micromixing model. The IEM‐inferred micromixing times were remarkably shorter by nearly four orders of magnitude in comparison with OMF and SMF excitations, and without magnetic field. The proposed mixing strategy is foreseen to complement innovative microfluidic devices with valuable mixing tools and methods for the diagnosis of the coupling between transport and intrinsic kinetics. © 2016 American Institute of Chemical Engineers AIChE J, 63: 337–346, 2017     

Biogenic Amine Contents in Non-alcoholic Beers: Screening and Optimization of Derivatization

A rapid, sensitive, and reproducible high-performance liquid chromatographic procedure for the determination of nine biogenic amines in non-alcoholic beers was developed by an optimized benzoylation procedure. A Plackett–Burman factorial design was used in order to screen the statistically significant variables. The significant factors of biogenic amine benzoylation, reagent volume and pH, were optimized by a complete factorial response surface design, and optimal reaction conditions were generated. The optimized method showed good linearity (correlation coefficients > 0.997) and good recoveries (from 88.6 to 104.7 %). The repeatability and reproducibility of method were >3.9 and >4.6 %, respectively. Moreover, the detection limits of biogenic amines were calculated between 0.05 and 0.15 μg/ml in wine samples. The optimized method has been applied to the determination of biogenic amine contents of non-alcoholic beers consumed in Iran. Their values ranged from 0 to 2.56 mg/l, no significant differences (p?>?0.05) were observed between the analyzed samples, and none of these samples surpass the toxic levels reported in the literature.     

A crossover‐UNIQUAC model for critical and noncritical LLE calculations

A new model, named the crossover‐UNIQUAC model, has been proposed based on the crossover procedure for predicting constant‐pressure liquid–liquid equilibria (LLE). In this manner, critical fluctuations were incorporated into the classical UNIQUAC equation. Coexistence curves were estimated for systems having a diverse range of asymmetries. These systems included the LLE of five different mixtures, composed of nitrobenzene with one of the members of the alkane homologous family (either pentane, octane, decane, dodecane, or tetradecane), as well as an extra system having a different chemical nature, namely the mixture of n‐perfluorohexane and hexane, to further check the validity of the proposed approach. Using these nonideal mixtures, the validity of the new model was investigated within wide ranges, covering near‐critical to regions falling far away from the critical point. The graphical trends, as well as the quantitative comparison with experimental data indicated the good agreement of the proposed model results with the experimental data. A maximum AARD% value of 3.97% was obtained in calculating molar compositions by the proposed model for such challenging systems covering noncritical, as well as critical regions. In addition, to show the strength of the proposed crossover approach to describe properties other than LLE, molar heat capacities were investigated for the system of nitrobenzene + dodecane. © 2015 American Institute of Chemical Engineers AIChE J, 61: 3094–3103, 2015